标签：#devto

When I built the MCP server for this project — it combines GitHub and DEV.to into a set of tools an agent can call — I had a decision to make before writing a single tool: talk to the low-level MCP protocol directly, or use FastMCP 's decorator API. I've seen a few "your first MCP server" writeups lately walk through the low-level path because it's more "honest" about what MCP actually is under the hood — JSON-RPC over stdio, a capabilities handshake, typed request/response schemas. That's true, and it's a reasonable thing to want to understand. But I want to write about the other side: what it actually costs you in practice once you have more than one or two tools, because I went through both and the difference showed up fast. what the low-level path actually asks you to write Strip away the decorator and MCP is a JSON-RPC server. For every tool you add, you're responsible for: Registering the tool's name, description, and a JSON Schema for its inputs in a list_tools handler Writing a call_tool dispatcher that matches on tool name and unpacks arguments by hand Serializing the return value into the TextContent / ImageContent wrapper types MCP expects Keeping the schema you wrote in step 1 in sync with the arguments you actually read in step 2, by hand, forever None of that is hard in isolation. The problem is it's boilerplate that scales linearly with tool count and has zero connection to the actual logic of the tool. My server has 8 tools. Hand-rolled, that's 8 schema blocks plus a dispatcher if/elif chain plus 8 response-wrapping calls, all of which exist purely to satisfy the protocol, not to do anything a GitHub or DEV.to API call needs. what it looks like with FastMCP Here's an actual tool from server.py , unedited: @mcp.tool () def get_repo_stats ( repo : str ) -> dict : """ Get stars, forks, watchers, open issues for enjoykumawat/<repo>. """ r = _gh ( f " /repos/ { GITHUB_USERNAME } / { repo } " ) return { " name " : r [ " name " ], " stars " : r [ " stargaze

Most "AI email" tutorials end with a while True loop that polls an inbox every thirty seconds, runs the new messages through a model, and sends a reply. It demos fine. Then you put it in front of real traffic and the cracks show up immediately: you're burning API calls to fetch nothing 99% of the time, your reaction latency is bounded by your poll interval, and the moment you scale to more than one inbox the polling cost multiplies. Polling an agent's inbox is wasteful. Webhooks are the right primitive for this. The mailbox already knows the instant a message lands — there's no reason to keep asking. What you actually want is a pipeline: inbound mail fans out to a verified ingest endpoint, lands on a queue, and gets picked up by workers that drive your agent runtime and send the reply. This post is about that architecture end to end — not a single feature, but the whole flow, with the parts that bite you in production (idempotency, retries, ordering, backpressure) called out honestly. I work on the Nylas CLI, so the terminal commands below are the exact ones I reach for when I'm wiring this up. I'll show the curl HTTP call and the CLI equivalent for every concrete step, because you'll use both: curl in your provisioning scripts, the CLI when you're poking at a live account. The mental model: an Agent Account is just a grant Before any of the pipeline matters, here's the one abstraction that makes the whole thing simple. An Agent Account is a Nylas grant — it has a grant_id , an inbox, an email address on a domain you own, and it speaks every grant-scoped endpoint you already know: Messages, Threads, Folders, Drafts, Attachments, Calendars, Events, Contacts, Webhooks. There's no OAuth token to refresh, no provider-specific quirks, no separate SDK. If you've built against a connected Gmail or Microsoft grant before, the data plane is identical. Nothing new to learn there. What's different is that the agent is a participant. It has its own address — support@yourcompany

Most posts about "AI email agents" stop at the happy path: webhook fires, model drafts a reply, agent sends it. Demo works, screenshot looks great, ship it. Then it goes to production and the agent replies to the same customer twice ninety seconds apart, and now your "intelligent assistant" looks like a broken cron job. That second reply isn't a bug in your model. It's a property of the delivery system, and it's guaranteed to happen eventually. Nylas webhooks are at-least-once: the same event can arrive up to three times. If your handler treats every POST as a fresh event, every retry is a second action. For a logging pipeline that's harmless. For an agent that sends email on your behalf , a duplicate delivery is a duplicate reply, and a double-reply embarrasses the agent in front of the exact person you built it to impress. So this post is about the engineering of idempotency itself, applied to an Agent Account. Not "remember to dedupe" hand-waving — the actual moving parts: which field is the real dedup key, how to persist processed ids atomically, why you ack before you work, how to make the send path itself idempotent, and where a per-thread lock catches the race that dedup alone can't. I work on the Nylas CLI, so every terminal command below is one I've actually run, verified against nylas v3.1.27. What an Agent Account changes (and what it doesn't) An Agent Account is just a grant. It has a grant_id and works with every grant-scoped endpoint — Messages, Drafts, Threads, Folders — exactly like a connected Gmail or Microsoft account. The difference is it's an inbox the agent owns : support@yourcompany.com is the agent, not a human whose inbox the agent borrows. Inbound mail to that address fires the standard message.created webhook, the agent reads it, and the agent replies from its own address. Nothing new to learn on the data plane. That's the whole point of the grant abstraction — the idempotency work below is plain webhook-handling discipline, and it transfe

Most "AI email" integrations assume everything on the other side speaks REST. You wire up a webhook, you call POST /messages/send , and you move on. That works right up until you remember how much of your stack doesn't speak REST and never will: the ticketing system that ingests mail over IMAP, the backup script your predecessor wrote in 2014, the monitoring tool that only knows how to send SMTP, the compliance archiver that polls a mailbox every five minutes. None of those are getting rewritten to call an HTTP API for your demo. So here's the trick that makes a Nylas Agent Account genuinely useful in a real environment: it's not API-only. You can expose the same mailbox over IMAP and SMTP submission , hand the host, port, and credentials to one of those legacy tools, and let it read and send like it's talking to any old mail server. Meanwhile your agent drives that identical mailbox over the v3 API. Both surfaces hit one storage layer. A flag, move, or delete on either side shows up on the other within seconds. I work on the Nylas CLI, so the terminal commands below are the exact ones I reach for. As usual I'll show both angles for every operation — the raw curl against the API and the nylas command — because half the point of an Agent Account is that you can mix them freely. What you actually get An Agent Account is just a grant . It has a grant_id , and that grant_id works with every grant-scoped endpoint you already know — Messages, Drafts, Threads, Folders, Attachments, Contacts, Calendars, Events. There's nothing new to learn on the data plane. The IMAP/SMTP layer doesn't change that model. It adds a second door into the same room: One mailbox, two protocols. The API and the IMAP/SMTP server are two front-ends over the same backend. There is no sync job, no eventual-consistency window worth worrying about, no "API mailbox" versus "client mailbox." It's one mailbox. Legacy tools just work. Anything that can authenticate to an IMAP server with a username and pas

A developer added an AI reviewer to a small Node and React project expecting an easy win. At first, the comments looked useful. Then the reviewer started repeating style complaints, commenting on code that had already changed, and missing a misplaced null check that crashed the application in staging. The team still had to perform a complete human review. That experience, shared in a public DevOps discussion, captures the real question engineering leaders should ask before adding an AI reviewer to every pull request: Did the reviewer remove work from the team, or did it create another thing the team had to review? The problem is not that AI review never works Developers report genuinely useful results too. In one Experienced Developers discussion, engineers described AI reviewers catching privacy leaks, incorrect data-flow assumptions, and logic errors that human reviewers had missed. In the same discussion, another engineer said their review bot was useful but produced plausible, inaccurate comments about one-third of the time. These are anecdotes, not a benchmark. But together they explain why the debate feels confused. AI review is not simply good or bad. Its value depends on the codebase, the context available to the reviewer, the kind of issue being reviewed, and how much verification its output requires. A tool can catch one subtle bug and still make the overall review process slower. It can also say nothing on several pull requests and then save a team from a serious failure. Counting comments cannot distinguish between those outcomes. Comment volume measures activity, not value GitHub says Copilot code review has completed more than 60 million reviews. Its definition of a good review has changed as that volume has grown. The team says it moved from optimizing for thoroughness to optimizing for accuracy, signal, and speed. GitHub reports actionable feedback in 71% of Copilot reviews. In the other 29%, the reviewer says nothing. That silence is intentional: if

I've been using TablePlus for years. It's good — but the connection limits on older licences drove me mad, and most alternatives are either Electron apps or haven't been updated since 2019. So I built my own. What is Stratum? Stratum is a native macOS database GUI — written in Swift, not wrapped in Electron. It connects to MySQL, MariaDB, PostgreSQL, and SQLite. What made me actually build it Three things: 1. Connection limits. TablePlus caps connections on older licences. Stratum has none. 2. Electron alternatives. Beekeeper Studio is good but it's an Electron app. On a Mac, that matters. 3. The MySQL setup friction. Most tools require you to install extra dependencies. Stratum connects natively — no brew install, no extra setup. What it does Table browser with inline editing — add, edit, delete rows without SQL Server-side pagination — stays fast on tables with 100k+ rows Query editor with schema-aware autocomplete Visual schema designer — create tables, add columns without writing DDL Full SQL export — DROP + CREATE + batched INSERTs iCloud sync for connections and snippets Laravel Valet auto-detection Import connections from TablePlus in one click SSH tunnelling The tech Built with SwiftUI and Swift 6. The PostgreSQL driver uses PostgresNIO. The MySQL driver implements the MySQL wire protocol directly over Network.framework — no Homebrew dependency, works inside the App Sandbox. Where it is now Currently in free beta. One-time purchase planned for the Mac App Store — no subscription. → stratum.mwn-digital.uk Happy to answer questions about how it's built.

This week's tooling news clusters around two themes that don't usually arrive together: token-efficient multimodal reasoning and infrastructure-level agent safety. The Inkling model launch dominates the conversation, but the more quietly significant story is Microsoft and Vercel independently shipping primitives that make running untrusted agent code and managing agent credentials meaningfully less dangerous. Here's what's worth your attention. Inkling mixture-of-experts model enables token-efficient reasoning Inkling is a decoder-only MoE with 1T total parameters and 40B active per token, native multimodal I/O (text, image, audio), and a reasoning_effort API parameter that lets you tune compute depth per request. It's live on Together Serverless today with no capacity queue. The practical upside is architectural simplification. If you're currently chaining a vision model, a transcription service, and a text LLM into a single reasoning pipeline, that's three API clients, three failure surfaces, and three billing relationships. Inkling collapses that into one endpoint. The reasoning_effort knob is the other interesting piece—per-request control over inference depth means you can spend tokens proportionally to task complexity rather than paying full reasoning cost on every call. The caveat: exact reasoning_effort parameter values aren't fully documented yet. Don't hardcode assumptions about accepted values into production before checking the official docs. Verdict: Evaluate. Worth spinning up against your current multimodal workload to benchmark latency and cost. Hold production migration until parameter documentation stabilizes. Inkling open model handles image, text, and audio natively This is the self-hosted side of the same model. The 1T-parameter MoE ships with day-0 support in transformers 5.14.0+ and SGLang, plus llama.cpp quantizations for teams that want to run trimmed variants. The catch is hardware: full NVFP4 precision requires 600GB VRAM; BF16 needs 2TB.

I have a script called git_commit.py in one of my repos. It shells out to claude -p with the staged diff, gets back a Conventional Commit message, and prints it. It's wired into a prepare-commit-msg git hook so every commit gets a pre-filled message for free. Small, dumb, useful. The first version had one instruction in the system prompt: "Output ONLY the commit message — no explanation, no markdown, no quotes." That's it. It worked fine for a while, and then one day a commit landed with a trailing Co-Authored-By: Claude <noreply@anthropic.com> line that I never asked for and definitely didn't want on a personal repo's history. I did the obvious thing first: I made the prompt more specific. SYSTEM = ( " You are a git commit message generator. " " Output ONLY the commit message — one line, no explanation, no markdown, no quotes, " " no co-author lines, no signatures, no AI references. " " Follow Conventional Commits: type(scope): subject. " " Types: feat, fix, docs, style, refactor, test, chore. " " Subject: imperative, lowercase, max 72 chars. " ) This is the same move I see everywhere: the CLAUDE.md file in that same repo has a line that says, in bold, "NEVER add Co-Authored-By: or any Claude/AI reference to commit messages." I've seen the same pattern in a dozen other people's prompt files — a growing list of "never do X" instructions bolted onto a system prompt, each one added reactively after X happened once. It helped. It did not solve it. A model call is a sample from a distribution, not a function with a guaranteed return type. Any single generation can still ignore an instruction — a longer diff, a different day, a subtly different phrasing of the request, and the same "never" line just doesn't fire. I don't actually know the mechanism on any given miss and I don't need to. The point is: a natural-language instruction is advisory. It shifts probability mass, it doesn't clamp it. I ran into an article on dev.to making a point that reframed this for me: the al

Last year my team had to pick a coding agent, and I volunteered to run the evaluation. I felt good about it. I pulled up the public benchmark scores, lined up the contenders, took the one at the top, and told everyone we had a winner. Then we actually pointed it at our repo. It did not blow up dramatically. It just kept being slightly wrong in ways that ate our time. It wrote diffs our reviewers would not approve. It renamed a function and broke three files it had never opened. The tests it ran passed, and the repo was still broken. I had confidently recommended a tool based on a number that turned out to say almost nothing about our situation. That was embarrassing enough that I went and figured out why. It took a few weeks of reading and a couple more bad calls before I landed on something that works. This is that, written plainly, and I hope it saves you the meeting where you have to walk your recommendation back. Why the benchmark score lied to me The score was not fake. It was just measuring somebody else's code. Once I looked properly, four gaps explained the whole thing: The agent might have already seen the answers. The problems in these public benchmarks are old. Models were very likely trained on the actual fixes used to grade them. So the score partly measures memory, not problem-solving. The setup is nothing like real work. A benchmark gives the agent a clean repo, one clear issue, and one command to run the tests. My engineers give it a half-open editor, a messy branch, a Slack thread, and a reviewer comment. Completely different job. Our codebase has its own habits. Our internal libraries, our wrappers, our test style, the imports we ban. No benchmark knows any of that, so an agent can write textbook-perfect code that our reviewers still reject on sight. The bar for passing is way lower. A benchmark passes a patch if the broken test now passes. My team passes a patch if it does that, and does not break unrelated tests, does not reformat the whole file,

My CLAUDE.md has one line near the bottom that I wrote months ago and mostly forgot about until I started actually paying attention to what it does: ## Important Note after your work done codex will review what you done. Terse, no punctuation, clearly typed in a hurry. But it's a real instruction that fires on every session in this repo: I finish a change, and a second model reviews it before I consider the work done. I added it half as an experiment. A few months in, it's changed how I work more than almost anything else in the setup, and not in the way I expected. I thought it would catch bugs. Mostly it doesn't, not directly. What it actually does is force a triage decision on every single piece of feedback, and getting that triage wrong is where all the pain lives. The three buckets Early on I treated every review comment the same way: read it, do it. That lasted about a week before I was silently making changes I didn't agree with because a second AI suggested them, and separately burning a stupid amount of time re-litigating comments that were just wrong or out of scope. What actually works is sorting every comment into one of three buckets before touching code: Fix it, no discussion. The comment is unambiguous, low-risk, and doesn't touch anything architecturally significant. Just do it and move on. Ask first. The comment is ambiguous, or it touches something that would require a real judgment call, or the "fix" would be a bigger refactor than the comment implies. Stop and get a human decision before acting. Skip silently. The comment is a duplicate of something already handled, or genuinely doesn't apply. Don't reply just to say "not doing this," don't leave a comment thread as evidence of having read it. Silence is the correct response to a non-issue. The failure mode I kept falling into before I had these buckets explicitly was collapsing 2 into 1: treating "ambiguous" as "just pick an interpretation and go." That's the actual source of review fatigue, not

When an autonomous agent gets an email address of its own, the first question your security team asks isn't "can it send mail?" It's "can you prove, six months from now, exactly what it said and to whom?" That's a different problem from "does it work." A demo that fires off a few support replies looks great in a sprint review. But the moment a real customer says "your bot promised me a refund," or a regulator asks for the complete record of what an automated system told a data subject, you need a defensible trail — an immutable record of every outbound and inbound message the agent touched, captured outside the mailbox the agent can also delete from. I work on the Nylas CLI, so the terminal commands below are the exact ones I reach for. But the architectural point here is provider-agnostic and it's the part most "AI email" tutorials skip: the live mailbox is not your audit log. It's mutable, it has retention limits, and the same agent that sends mail can also trash it. If your only record of what the agent did lives in the inbox, you don't have an audit trail — you have a working copy. What "audit-log everything" actually means There are two stores in this design, and keeping them separate is the whole point. The live mailbox — the Agent Account grant. Messages flow in and out here. It's queryable, it's real-time, and it's mutable . Flags change, messages move folders, things get trashed. On the free plan it's also retention-limited: 30 days for the inbox, 7 days for spam. The audit store — your system. An append-only, write-once log keyed by message_id and thread_id . Nothing in it is ever updated or deleted in normal operation. This is the record you hand a reviewer. The audit store is the thing you build. Nylas gives you the two capture points — the send response and the inbound webhook — but the immutability is your responsibility. That means a WORM (write-once-read-many) object store, an append-only table with no UPDATE / DELETE grant for the app role, or a has

Most multi-tenant SaaS apps that send email do it from one shared identity. There's a notifications@yourapp.com , every customer's mail flows through it, and the tenant is just a from_name you stamp on the subject line or a footer you swap out. That's fine until it isn't — until Tenant A's spam complaints drag down Tenant B's deliverability, until a reply from a customer lands in a single firehose inbox you now have to fan back out, until one tenant wants a stricter send cap than another and you realize you built none of that into the data model. So let's not share. Let's give every tenant its own real mailbox — a dedicated Agent Account per customer, each with its own grant_id , its own send identity, its own policy and limits, grouped into its own workspace. Not one inbox with a thousand label hacks. A thousand inboxes, isolated by construction. I work on the Nylas CLI, so the terminal commands below are the exact ones I reach for when I'm wiring this up. Every step gets the two-angle tour: the raw curl call and the nylas command that does the same thing. Why per-tenant beats one shared sender The shared-sender model fails along a few predictable seams. Per-tenant Agent Accounts close each one: Deliverability blast radius. When everyone sends from one address, one tenant's bounce rate and spam complaints poison the reputation everyone shares. Per-tenant accounts — and, if you want, per-tenant domains — keep one customer's bad behavior from sinking the rest. Inbound that actually belongs to someone. A shared sender means replies come back to one mailbox and you're left correlating them to tenants by hand. When each tenant has its own grant, an inbound message.created event already carries the grant_id . The routing is done before your handler runs. Per-tenant policy and limits. Different customers, different rules. A trial tenant capped at a low daily send; an enterprise tenant with a higher quota and longer retention. With a shared sender you'd build all of that y

Most teams test email by not testing it. The send path gets a mock — expect(transport.send).toHaveBeenCalledWith(...) — and everyone agrees that's "good enough." The receive path gets skipped entirely, because there's no honest way to assert on a real inbox from a test runner. So the one part of your system that talks to the outside world over an unreliable, asynchronous, third-party channel is the part with the least coverage. That's backwards. The reason email is hard to test isn't the sending. It's the asserting . You can fire POST /messages/send all day, but to prove the message actually left, rendered correctly, and arrived with the body you expected, you need a real mailbox you control — one you can read programmatically and throw away when the run finishes. Shared Gmail test accounts almost get you there, but they bring OAuth on the runner, catch-all races between parallel workers, and a 90-day token that expires the night before a release. This post is about a different fixture: a disposable Agent Account created at the start of a CI run and deleted at the end. You mint a real mailbox per run (or per test), point your application at it, send and receive real mail, assert on the actual message body, and tear the whole thing down. No OAuth. No shared inbox. No leftover state. What an Agent Account gives you here An Agent Account is just a Nylas grant with a grant_id . That's the whole trick, and it's worth saying plainly because it's what makes this pattern cheap: an Agent Account works with every grant-scoped endpoint you already know — Messages, Drafts, Threads, Folders, Attachments, Webhooks. There's nothing new to learn on the data plane . If you've ever called GET /v3/grants/{grant_id}/messages , you already know how to read a test inbox. The difference from a normal grant is provisioning. A regular grant needs a real human to complete an OAuth flow. An Agent Account is created with a single API call — no OAuth screen, no refresh token, no human. It's a m

Most "AI email agent" demos end with a triumphant send . The model writes a reply, the code POSTs it, and a real message lands in a real stranger's inbox. That's a great demo and a terrible production default. The moment your agent can send mail with nobody watching, you've handed an LLM a corporate email address and the standing authority to use it. One hallucinated price, one confidently wrong refund promise, one apology to the wrong customer, and you're explaining to legal why a bot signed an email as your company. There's a boring, durable fix that predates AI by decades: don't send — draft. Stage the message, put a human in front of it, and only send once someone with a name and a pulse approves. Email systems have had a "Drafts" folder forever for exactly this reason. The Nylas Drafts API turns that folder into something better — an approval queue your agent writes into and your reviewers drain. This post builds that queue. The agent creates a draft, a human reviews the pending drafts, and an approved draft gets sent byte-for-byte unchanged . No re-rendering, no "the agent regenerates it on approval" race where the thing you approved isn't the thing that ships. I work on the Nylas CLI, so the terminal commands below are the exact ones I reach for, and I'll pair every one with the raw curl so you can wire it into a backend in whatever language you like. This is deliberately not about escalating inbound threads to a human (that's a different problem, where the trigger is a message arriving). Here the trigger is the agent wanting to send , and the gate sits on the outbound path. Why a draft is the right approval primitive You could build approval a dozen ways. You could buffer the agent's output in a queue table and call send later. You could stash a JSON blob in Redis. Both work, and both quietly reinvent something the email stack already gives you. A draft is a real, persisted email object , on the mailbox, with a stable id . That buys you three things a homegr

Hi guys, I've been working on Regdrift, my first open-source project. It's a CLI and GitHub Action that compares two CMSIS-SVD files to check whether there are any register-map changes that could affect firmware functionality. It catches changes such as moved registers, interrupt renumbering, access changes, and altered read/write behavior. It then classifies those changes as BREAKING , WARNING , or SAFE so the tool can act as a CI gate. I'm looking for feedback from people who maintain SVDs, HALs, PACs, SDKs, or firmware repositories. If possible, I'd like to test it against real old/new SVD pairs and learn where the classifications produce false positives, miss important changes, or are unclear. For people who work frequently with CMSIS-SVD files: which types of register-map changes are most detrimental to firmware or cause the most difficult code-related problems? Resources GitHub: https://github.com/Pranav-s79/regdrift Install pip install regdrift Usage regdrift check old.svd new.svd

Getting an AI API request to return a response is only the beginning. For real AI products, the harder question is what happens when something goes wrong. A chatbot may become slower. A RAG answer may stop using the right context. A structured extraction workflow may start returning invalid JSON. An agent may trigger the wrong tool. A fallback model may answer correctly, but at a much higher cost. In a single-model prototype, debugging is usually simple. You check one provider, one API key, one model, and one request format. In a multi-model application, debugging becomes an infrastructure problem. A product may use GPT for one workflow, Claude for another, Gemini for multimodal tasks, DeepSeek for cost-sensitive reasoning, Qwen or Kimi for Chinese-language workflows, GLM for enterprise scenarios, and MiniMax or Doubao for other product features. When something fails, developers need to know more than whether the API returned an error. They need to know which workflow failed, which model handled it, whether fallback happened, whether latency changed, and whether the final output was still good enough for production. Why multi-model debugging is different AI API failures are not always clean outages. Sometimes the request fails completely. But many production issues are softer: latency increases structured output fails validation tool calls become unstable fallback routes trigger too often answers become less grounded costs increase silently one language performs worse than another a model works for chat but fails for agent workflows That is why teams should not treat AI debugging as simple error handling. They need visibility across the full request path. Start with a failure taxonomy The first step is to classify failures in a way developers can act on. A useful AI API failure taxonomy may include: authentication errors rate limits quota limits timeout errors model unavailable errors high latency responses invalid JSON output schema validation failures tool call fa

Image-to-video generation is often described as a simple interaction: upload image -> describe motion -> get video That description hides the real problem. A single still contains only one view of a subject. When we ask a model for a fast camera orbit, a full-body walk, or expressive gestures, we are asking it to invent information that was never present in the source. That is where identity drift, unstable lighting, texture flicker, and waxy faces come from. The useful way to approach Seedance 2.0 image-to-video is not as a prompt-writing contest. It is a constraint-management workflow. Give the model a strong identity anchor, request motion that the source image can support, and evaluate one variable at a time. This post explains that workflow in a way that is useful whether you are animating a product render, a character portrait, an approved client still, or a visual asset for a prototype. Note: Model capabilities, pricing, model availability, and input limits change quickly. Check the current documentation and the terms of the platform you use before committing a production workflow. Why image-to-video is different from text-to-video Text-to-video is excellent when invention is the point. You describe a scene and let the model make creative decisions about characters, lighting, composition, and motion. Image-to-video is the better tool when those decisions have already been made and must remain stable. Situation Better starting mode Why Product hero shot Image-to-video Label, shape, material, and color must remain recognizable Character-led sequence Image-to-video One strong reference can anchor a character across clips Approved campaign still Image-to-video The source already represents the accepted art direction Atmospheric B-roll Text-to-video Exact subject identity matters less than visual exploration Abstract concept film Text-to-video Inventing a scene is more valuable than preserving one Existing brand-photo library Image-to-video Stills become reusable

If you've ever bid on a public sector contract, you know the PQQ drill. Someone sends you a Word document with 47 questions spread across 6 sections. Company info. Technical capability. Financial standing. Health & safety. References. Maybe something about modern slavery or carbon reporting because it's 2026 and everything has to check everything. You have to: Read every question Figure out what category it falls under Decide which ones are easy and which will take a week Dig up the right evidence for each one Track word limits And you're doing this at 10pm because the submission deadline is Friday. I got tired of doing this manually, so I built a free tool that does it in one click. What it does PQQCheck takes any PQQ document — pasted raw, formatting and all — and runs it through an LLM that understands procurement documents. It returns: Every question extracted — no more re-reading the document to check you didn't miss one Category tags — Technical, Financial, H&S, Insurance, etc. Difficulty ratings — Easy / Medium / Hard at a glance so you know where to start Suggested evidence — what to prepare for each question Word limits — pulled straight from the document Here's what the output looks like: | Question | Category | Difficulty | Suggested Evidence | Limit | |-----------------------------------|-------------|------------|----------------------------|-------| | Provide your registered name & no | Company | Easy | Certificate of Incorporation | 50 | | Describe IT managed services exp | Technical | Hard | 3 case studies + CVs | 500 | | Provide H&S policy | H&S | Easy | Current policy document | — | | ISO 27001 certification details | Technical | Medium | Certificate + scope doc | 200 | Why this matters for procurement teams Most PQQ response planning is reactive. You read the document, start answering, and discover mid-way that a question needs a certificate you don't have or a reference you can't get in time. PQQCheck flips that. You know before you start writing

Most "AI email" demos never think about deletion. The agent reads, replies, files things away, and the inbox just grows. That's fine in a demo. It is a problem the first time a real person emails your agent, because the moment that mailbox holds someone else's name, address, order history, or support complaint, you've taken on a data-protection obligation — and "we kept everything forever" is not a defensible retention policy. An Agent Account on Nylas accumulates personal data you have to be able to purge. It's a mailbox the agent owns — support@yourcompany.com answering to a model instead of a human — and every inbound message lands in it. Under GDPR that data needs two things you can prove: a retention window so it doesn't live forever, and an erasure path so you can delete a specific person's mail when they ask. This post builds both, with the curl and the CLI for each step. A quick, honest caveat before any of it: this is a docs-and-demo walkthrough, not legal advice. The Nylas primitives below cover the mail held in the mailbox . Any derived copy you made — rows in your own database, lines in your application logs, a vector store you embedded the message into — is yours to purge separately. The API can delete the message; it can't reach into your Postgres. Keep that in mind throughout. What the platform gives you Nothing new to learn on the data plane. An Agent Account is just a grant with a grant_id , so everything you already know about Messages and Threads applies directly — listing, reading, and deleting mail run against the same grant-scoped endpoints any other Nylas integration uses. Retention and erasure split cleanly into two layers: Retention is a control-plane setting. It lives on a policy — an application-scoped resource that bundles limits and spam settings — attached to the workspace your Agent Account belongs to. Two fields cap how long mail survives: limit_inbox_retention_period and limit_spam_retention_period . Set them once and Nylas deletes a

Spam traps are the failure mode nobody puts in the demo. A bounce is loud — you get a 5.x.x back, your code logs it, you move on. A complaint at least gives you a webhook. A spam trap gives you nothing . The message gets accepted, no error comes back, and somewhere a mailbox provider quietly writes your domain down as a spammer. By the time you notice, your inbox placement has already cratered and you have no single bounce to point at. That's the trap, literally. And it's the one that bites autonomous agents the hardest, because the whole appeal of an agent is that it acts without a human watching every send. Point a model at a list it scraped, let it loop, and it'll happily mail a recycled address that's been a trap for two years. The agent never sees a problem. You only see the aftermath in your deliverability dashboard a week later. I work on the Nylas CLI, so the terminal commands below are the exact ones I reach for when I'm wiring up an Agent Account to not do this. The good news is that an Agent Account is just a grant — a grant_id that works with every grant-scoped endpoint you already know — so there's nothing new to learn on the data plane. The defense is mostly discipline: validate before you send, honor every complaint, and age out the addresses that never wanted to hear from you. What a spam trap actually is, and why it's not a bounce It's worth being precise here, because the three things people lump together behave completely differently. A bounce is a rejected delivery. The receiving server tells you the address is bad, you get a message.bounced event, and you stop. Bounce handling is a solved problem — you listen, you suppress, you're done. A complaint is a recipient hitting "report spam." The mailbox provider relays that back as a feedback loop, and you get a message.complaint event. The address is real and reachable; the human just doesn't want your mail. If you keep mailing them, you're training the provider to filter you. A spam trap is neither.