标签：#solana

This is a submission for Weekend Challenge: Generosity Edition What I Built My late...

One SQL statement over a VECTOR(768) column, 45,400 charities, and 2,917,459 real pairs used to check it. What the detector caught, and what it missed.

This is a submission for the DEV Weekend Challenge: Generosity Edition. What I...

I Built an Autonomous AI Agent That Hunts Bounties. Here's What Happened. The Setup I gave an AI agent one job: find paid work online, build the deliverable, and earn money — autonomously. Not a chatbot. Not a copilot. An agent that scans 232+ listings across multiple platforms, filters out scams and ghost sponsors, writes proposals, generates deliverables with real market data, and queues everything for human approval. Here's what happened in the first 48 hours. The Stack (All Free) Python core — pipeline orchestration, economic gate, critic Ollama + qwen3:4b — local LLM for analysis writing (no API costs) Chart.js — dashboard visualizations Public APIs — CoinGecko, DeFiLlama, Solana RPC (all keyless) GitHub Pages — free hosting for the portfolio Windows Task Scheduler — runs every day at 9 AM + every 4 hours Total infrastructure cost: $0/month. What the Agent Actually Does Every Morning 09:00 — Wake up ├── Check-in on AgentHansa (earn $0.01 USDC daily drip) ├── Scan Superteam Earn (232 live listings) ├── Scan Clawlancer/TaskForce/MoltJobs for gigs ├── Scan GitHub for paid issues ($20-500 fixes) ├── Filter through 7 anti-scam layers: │ geo restrictions, human-presence demands, │ ghost sponsors (no web/twitter/verification), │ unverified payers, real-money requirements ├── Economic gate: expected value must be positive ├── Local LLM critic reviews against actual page content └── If candidate passes everything: → Build deliverable (report/dashboard/thread draft) → Generate proposal text → Send Telegram alert with approval command The Filters That Saved Me In the first 24 hours, the agent found 232 listings. After filtering: Filter Killed HUMAN_ONLY access 216 Ghost sponsors (no identity) 1 (would've wasted hours) Real-money deposit required 1 ($1000 bug bounty trap) Country walls 1 (Superteam Canada only) Already claimed/stale Rest Without these filters, I would have wasted days on bounties that were never going to pay. The First Deliverable The agent found a $500 bo

Originally published on xroot.dev . In high-frequency Web3 infrastructure, relying on a TypeScript SDK or a third-party pricing API means you are already too late. If you are building an arbitrage bot, a sniper, or a real-time indexer on Solana, reading data through abstracted REST endpoints introduces hundreds of milliseconds of latency. To build institutional-grade infrastructure, you have to bypass the middleman. You need to pull the raw binary state of the Automated Market Maker (AMM) directly from the RPC node and deserialize it natively in memory. Here is how to reverse-engineer Solana DeFi pools and parse raw account data in Rust at microsecond speed. The Anatomy of a Solana Account & The Anchor Discriminator Beneath the abstractions of the Solana ecosystem, an account's data is fundamentally just a continuous array of bytes ( &[u8] ). When a smart contract writes to an account, it serializes its state into this raw byte buffer. If the AMM was built using the Anchor framework — which the vast majority of modern Solana DeFi protocols are — the account data doesn't just start with the struct variables. Anchor prepends an 8-byte discriminator to the beginning of the data payload. This discriminator is calculated using the first 8 bytes of the SHA256 hash of the string "account:StructName" . It acts as a safety check: if you try to deserialize an AMM pool account but the first 8 bytes don't match the expected hash, the program knows you passed the wrong account type and immediately aborts. Bytes 0–7 (Anchor Discriminator) → Bytes 8–N (Raw struct data (Borsh-serialized)) To parse the account data yourself, your first step is always identifying and slicing off those first 8 bytes. Reverse-Engineering the AMM Struct You cannot parse binary data without knowing its exact memory layout. We need to map the byte layout of the DeFi pool — such as a Raydium CPMM or a pump.fun bonding curve — into a tightly packed Rust struct . Instead of paying the "Borsh tax" (the CPU ov

I Built an Autonomous AI Agent That Hunts Bounties. Here's What Happened. The Setup I gave an AI agent one job: find paid work online, build the deliverable, and earn money — autonomously. Not a chatbot. Not a copilot. An agent that scans 232+ listings across multiple platforms, filters out scams and ghost sponsors, writes proposals, generates deliverables with real market data, and queues everything for human approval. Here's what happened in the first 48 hours. The Stack (All Free) Python core — pipeline orchestration, economic gate, critic Ollama + qwen3:4b — local LLM for analysis writing (no API costs) Chart.js — dashboard visualizations Public APIs — CoinGecko, DeFiLlama, Solana RPC (all keyless) GitHub Pages — free hosting for the portfolio Windows Task Scheduler — runs every day at 9 AM + every 4 hours Total infrastructure cost: $0/month. What the Agent Actually Does Every Morning 09:00 — Wake up ├── Check-in on AgentHansa (earn $0.01 USDC daily drip) ├── Scan Superteam Earn (232 live listings) ├── Scan Clawlancer/TaskForce/MoltJobs for gigs ├── Scan GitHub for paid issues ($20-500 fixes) ├── Filter through 7 anti-scam layers: │ geo restrictions, human-presence demands, │ ghost sponsors (no web/twitter/verification), │ unverified payers, real-money requirements ├── Economic gate: expected value must be positive ├── Local LLM critic reviews against actual page content └── If candidate passes everything: → Build deliverable (report/dashboard/thread draft) → Generate proposal text → Send Telegram alert with approval command The Filters That Saved Me In the first 24 hours, the agent found 232 listings. After filtering: Filter Killed HUMAN_ONLY access 216 Ghost sponsors (no identity) 1 (would've wasted hours) Real-money deposit required 1 ($1000 bug bounty trap) Country walls 1 (Superteam Canada only) Already claimed/stale Rest Without these filters, I would have wasted days on bounties that were never going to pay. The First Deliverable The agent found a $500 bo

Originally published on xroot.dev . On-chain, a regulated fund token and a honeypot scam are the same shape. Both are Token-2022 mints. Both keep an active freeze authority. Both set DefaultAccountState to Frozen , so every new holder's account starts locked. One of them is a European money-market fund following its regulator's rules; the other is a trap built to let you buy and never sell. Every token scanner I tested reads them identically: red flags, high risk, score zero. The reason this now matters is sRFC-37, the Token ACL standard — the Solana Foundation's official mechanism for permissioned tokens. It has been live on mainnet since March 2026, real institutional money already uses it, and the entire real-world-asset wave forming on Solana is going to ship in this exact shape. This post covers how it works end to end — and the structural check that separates a compliant token from a trap, verified against the chain rather than anyone's metadata. Why Permissioned Tokens Exist at All A tokenized treasury fund, a regulated stablecoin, a security token — their issuers are not allowed to let anyone hold them. KYC requirements, sanctions screening, court orders, investor-accreditation rules: the issuer must be able to control who holds the asset and stop specific wallets, or the asset cannot legally exist on a public chain. Solana had two ways to build that before, and both hurt: Transfer hooks run issuer code on every transfer — but every DEX, wallet and protocol touching the token must implement the hook interface, so composability dies at exactly the venues that create liquidity. Manual freeze-and-thaw keeps standard transfers — but every new holder starts frozen and waits for the issuer to co-sign a thaw. Onboarding becomes a support ticket, and the issuer signs forever. Token ACL is the third path: keep the freeze mechanism — the one lever the token program already enforces everywhere — but make thawing self-service against a published rulebook. The Mechanics:

I Built an Autonomous AI Agent That Hunts Bounties. Here's What Happened. The Setup I gave an AI agent one job: find paid work online, build the deliverable, and earn money — autonomously. Not a chatbot. Not a copilot. An agent that scans 232+ listings across multiple platforms, filters out scams and ghost sponsors, writes proposals, generates deliverables with real market data, and queues everything for human approval. Here's what happened in the first 48 hours. The Stack (All Free) Python core — pipeline orchestration, economic gate, critic Ollama + qwen3:4b — local LLM for analysis writing (no API costs) Chart.js — dashboard visualizations Public APIs — CoinGecko, DeFiLlama, Solana RPC (all keyless) GitHub Pages — free hosting for the portfolio Windows Task Scheduler — runs every day at 9 AM + every 4 hours Total infrastructure cost: $0/month. What the Agent Actually Does Every Morning 09:00 — Wake up ├── Check-in on AgentHansa (earn $0.01 USDC daily drip) ├── Scan Superteam Earn (232 live listings) ├── Scan Clawlancer/TaskForce/MoltJobs for gigs ├── Scan GitHub for paid issues ($20-500 fixes) ├── Filter through 7 anti-scam layers: │ geo restrictions, human-presence demands, │ ghost sponsors (no web/twitter/verification), │ unverified payers, real-money requirements ├── Economic gate: expected value must be positive ├── Local LLM critic reviews against actual page content └── If candidate passes everything: → Build deliverable (report/dashboard/thread draft) → Generate proposal text → Send Telegram alert with approval command The Filters That Saved Me In the first 24 hours, the agent found 232 listings. After filtering: Filter Killed HUMAN_ONLY access 216 Ghost sponsors (no identity) 1 (would've wasted hours) Real-money deposit required 1 ($1000 bug bounty trap) Country walls 1 (Superteam Canada only) Already claimed/stale Rest Without these filters, I would have wasted days on bounties that were never going to pay. The First Deliverable The agent found a $500 bo

Finding grants means digging through 50 scattered Discords, blogs, websites, and Notion pages. So I built a fix. Meet Web3 Accelerator GrantHub (W3AGH). What is GrantHub? GrantHub is a web app that helps Web3 founders discover funding opportunities without digging through dozens of scattered websites. Grants are listed across ecosystems like Solana, Ethereum, Polygon, BNB Chain, Arbitrum, Base, and more. The idea is simple: instead of spending hours searching for funding opportunities, you should be able to find relevant grants in one place. GrantHub also has AI tools that sit on top of the grant database. You can describe your project once and instantly see which grants fit best. Why GrantHub? Funding is the lifeblood of Web3 startups, but finding grants today is painful. Scattered listings Every ecosystem publishes its own programs on its own website, blog, Discord, or other channels. There is no single source of truth. Stale information Grants expire, close, or change their requirements, while the listings founders rely on can remain outdated. Manual matching A founder has to read through each grant's requirements and figure out whether their project qualifies. With dozens of grants available, that can quickly turn into hours of work. No personal workflow There is no single place to save interesting grants, track applications, or ask questions about a specific program. GrantHub is built around solving these problems. It combines three things: One central catalog of grants stored in a real database. Personal tools: accounts, favorites, and a personal dashboard. AI assistance: a grant ranking engine, an AI assistant, a smart-contract auditor, and context-aware chat on every grant page. Who is this for? Solo builders and startups: looking for funding or ecosystem support. Beginners who don't yet know which ecosystems and grants are right for them. Anyone who would rather spend their time building than hunting for funding. The goal isn't to create another directory o

Building smart contracts on Solana using Rust and the Anchor framework requires a mindset shift from traditional Web2 backends. This week, I built a counter program, broke it on purpose, and used my test suite to verify that my security constraints were truly load-bearing. Here is how the program works under the hood and why every test in the suite exists. The Initialize Accounts Struct In Anchor, security boundaries are enforced before your instruction logic ever runs. The Initialize context defines three main accounts: counter : Initialized as a new on-chain account allocated with exact bytes (8 bytes for Anchor's discriminator, 32 for the authority's public key, and 8 for the count value). authority : Marked as a mutable signer who pays the account creation rent. system_program : The native Solana System Program required to execute account creation. Handler Logic & Constraints Because Anchor handles account creation and validation in the background, handler logic remains minimal. Initialize Handler The initialize handler receives the context, sets the counter account's authority field to match the transaction signer's public key, and sets the initial count state to zero. Increment Instruction with Constraints For the increment logic, Anchor uses an account constraint: has_one = authority , directly on the account context. This guarantees that the key in counter.authority matches the signer's wallet before any custom code executes. If an unauthorized wallet attempts to trigger an increment, Anchor rejects the transaction immediately at the constraint level. Testing the Happy and Failure Paths To prove these security checks work, I wrote unit tests for both valid execution and unauthorized attempts using LiteSVM. 1. Happy Path: Successful Initialization The Test: Executes the initialize instruction and asserts that the fetched account's count value equals zero. Why it exists: If space allocation fails or account deserialization breaks, this test fails because the o

One hundred days ago, I had no idea this challenge would become one of the most rewarding technical journeys I've taken. There were days when everything clicked, and there were days when nothing compiled. I celebrated successful deployments, stared at cryptic errors for hours, rewrote programs that weren't good enough, and learned that understanding Solana has far less to do with memorizing APIs than changing how you think about state, ownership, and security. Looking back now, I realize I didn't just complete 100 challenges; I built a completely different mental model of software. Where I started I came in with a biochemistry degree I never used, a self-taught engineering career I built in public, and a GitHub full of Rust and Python work. I co-maintain statix, a Nix linter that ended up in the canonical NixOS/nixpkgs upstream. I had shipped real software before. What I did not have was any intuition for how Solana actually works. I knew the buzzwords. I had the mental model of "it's fast and cheap." I did not know what an account was. I did not know what a program was. I did not know why those two things were different. That gap, between knowing the words and understanding the model, is what these 100 days actually closed. What I expected I expected Solana to feel like a database with extra steps. In Web2, you have a server that holds state. You call an API. The server reads from the database, does something, writes back. I expected a blockchain to be the same thing, just slower and decentralized. The first thing that broke that model: accounts. On Solana, an account is not a row in your database. It is the database. Every piece of state, your wallet balance, a token you hold, the program you deployed, is an account. Programs are accounts. Data is accounts. Everything is an account. That sounds obvious written down. It took me until around Day 15 to actually feel it, when I was staring at a getAccountInfo call wondering why the program I deployed was also an accou

100 Days of Solana, Day 100 Where I started I'd built REST APIs for years but had never touched a blockchain, or written a line of Rust. The curiosity how blockchain works, started my curiosity. What I expected I came in with a Web2 instinct: tests exist to prove your code does what it's supposed to do. Write the function, write a test that calls it, watch it pass, move on. A "failing test" was something you fixed, not something you shipped on purpose. What changed my understanding The moment this cracked open was building the capstone: a small Anchor program called proof-of-ship that lets a wallet permanently record, on chain, that it shipped something. The rule is simple — one ship record per wallet, forever. The rule lives entirely in the account's seeds: seeds = [ b"ship" , builder .key () .as_ref ()], bump Each wallet's record lives at one deterministic address. Try to create a second one, and init refuses, because an account already exists there. I wrote two tests. The first proved the happy path: call ship() , fetch the record, confirm the name and builder match. The second test is the one that changed how I think about testing: it ( " only lets each wallet ship once " , async () => { let rejected = false ; try { await program . methods . ship ( " Second try " , " This should never land " ). rpc (); } catch ( _err ) { rejected = true ; } assert . isTrue ( rejected , " second ship should have been rejected " ); }); This test isn't checking for a bug. It's checking that a rule holds. There's no function in my program called preventDuplicateShip() . There's no if statement rejecting the second attempt. The rule "one ship per wallet" isn't enforced by logic I wrote — it's enforced by the Solana runtime itself, because the PDA's address already has data in it. My job wasn't to write the rejection. My job was to prove the rejection actually happens. What I understand now On Web2 systems I controlled the whole stack, so "does it work" mostly meant "does the happy pa

When I set out to build a provably-fair random selection system on Solana, the obvious choice for randomness was a VRF (Verifiable Random Function). Instead, I built the system around Solana's SlotHashes sysvar with a commit-reveal scheme. Here's why, and what I gave up to get there. The problem A fair-selection system needs a winner (or set of winners) chosen in a way that's fair, and just as important that participants can check for themselves without taking anyone's word for it. VRF services (Switchboard, ORAO, etc.) solve the fairness part well: they produce randomness that's unpredictable in advance and cryptographically provable after the fact. But they come with a dependency on an oracle, a fee per request, and a proof that most users will never actually verify they'll trust it because the crypto math says they can, not because they did. I wanted something a participant with no crypto background could check in a browser console. The approach: commit-reveal with slot hashes The core idea: commit to the participant list before you know the randomness, then derive the randomness from a slot hash you couldn't have predicted at commit time. rust fn derive_randomness(target_hash: &[u8; 32], participant_root: &[u8; 32]) -> [u8; 32] { let mut combined_seed = [0u8; 64]; combined_seed[..32].copy_from_slice(target_hash); // slot hash at reveal combined_seed[32..].copy_from_slice(participant_root); // Merkle root, locked at commit solana_keccak_hasher::hash(&combined_seed).to_bytes() } The flow: Commit: participant list is finalized and hashed into a Merkle root; this is written on-chain. Wait: a target slot in the future is chosen as the reveal point. Reveal: once that slot passes, its hash is pulled from SlotHashes and combined with the committed root to derive the randomness. Select: the randomness deterministically picks winners from the participant set; winners get their own Merkle root and proofs. Every draw ends up with an audit record like: rust pub struct AuditR

Three weeks from now I will open a terminal, ready to ship another program to mainnet-beta, and I will pause. What was the order again? Did the IDL go up before or after the authority transfer? Was there a flag that saved me from a stalled deploy last time? This checklist exists because I just walked the entire path devnet to mainnet, deploy to IDL to frontend to error handling, and I wrote it down while the details are still fresh. It is the document I wish I had on day one of that process. Run it top to bottom before every mainnet launch. Why a checklist at all? A Solana mainnet deploy is full of irreversible steps. The wallet that signs the deploy quietly becomes the program's upgrade authority. A buffer account left mid-deploy can strand real SOL. A plain anchor build after a verifiable build can produce a different hash and break verification later. None of these are complicated. They are all easy to forget under pressure. A checklist is not a crutch; it is the habit that lets you ship calmly instead of improvising each time. Phase 1: Pre-flight on devnet Do all of this while mistakes are still free. [ ] Every test passes against the final build. Run anchor build && cargo test --package <your-program> one last time. The binary you test must be the binary you ship. [ ] End-to-end run on devnet. Call every instruction through the actual frontend, not just the test suite. The frontend is a different caller than LiteSVM and will surface different failure modes. [ ] Produce a verifiable build. Run anchor build --verifiable . This pins the build environment so the on-chain bytecode can later be matched to your source code. Once you have this artifact, do not touch it with a plain anchor build or cargo build-sbf ; those can produce a different hash and silently break verification. [ ] Measure rent before you spend it. Run: solana rent $( wc -c < target/deploy/.so ) Your deploy wallet must hold this amount plus a margin for transaction fees. There is no airdrop on the

Arc 11 covered Days 71–77 of Epoch 3, and it was all about Cross-Program Invocations. In Arc 9, we wrote our first Solana program. In Arc 10, we gave that program a more useful state model with Program Derived Addresses. But our programs were still mostly working alone. They could read and update their own accounts, enforce their own constraints, and respond to instructions sent by a client. They could not directly change state owned by another program or bypass the rules that program enforced. That is an important part of Solana’s security model. The System Program owns the rules for creating accounts and transferring lamports. Token-2022 owns the rules for mints, token accounts, supply, and mint authorities. If our program needs one of those capabilities, it calls the program that owns the operation. That call is a Cross-Program Invocation, or CPI. The Web2 comparison is a service-to-service API call. One service sends a request through another service’s public interface, and the receiving service applies its own rules. A CPI works in a similar way, with one important difference: the outer and inner instructions execute as part of the same Solana transaction. If the inner call fails, the state changes made by the outer instruction are rolled back too. That combination of clear program boundaries and atomic execution is what makes Solana programs composable. Our first CPI called the System Program The arc began with the smallest useful CPI we could build. Our Anchor program accepted a sender, a recipient, and an amount of SOL to transfer. But the program did not edit the sender’s balance directly. Instead, it called the System Program’s transfer instruction. That distinction matters. Accounts on Solana are owned by programs, and the owner program controls how their data may be changed. Our program could not simply reproduce the effect of a System Program transfer by adjusting balances itself. It had to ask the System Program to perform the operation. Every CPI need

I spent the last two weeks thinking like an attacker. I wrote tests whose only job was to make my own programs fail. I ran a fuzzer across thousands of generated inputs looking for the lamport value nobody would choose by hand. And I rebuilt the missing owner check that was at the center of the $326M Wormhole exploit, in a throwaway program, in a test, so I could watch it work and then watch the one-line fix stop it cold. This checklist is what I would hand to past me on day one of that work. Run it top to bottom before any Anchor program goes to mainnet. Who this is for You are writing Solana programs in Anchor. You understand accounts, PDAs, and CPIs. You have read the Anchor docs. What you do not yet have is a systematic way to check that you have not missed the failure modes that are specific to Solana's runtime, an account model where any account can be passed into any instruction, arithmetic that wraps silently in release builds without protection, and cross-program calls that trust whatever program ID you hand them. This checklist is that systematic check. It is not a substitute for a professional audit on high-value programs. It is the thing you run before you even consider requesting one. The Wormhole anchor Before the list, the story that explains why account validation sits at the top. In February 2022, an attacker drained $326M from the Wormhole bridge. The root cause was a single deprecated function, load_instruction_at — that read a sysvar account's contents without first checking that the account was actually the real instructions sysvar. The attacker passed in a forged account they controlled. The program read it, trusted it, and authorized a mint it should have refused. The fix was a single word: switch to load_instruction_at_checked , which verifies the account's address before reading it. Every item in this checklist traces back to that same principle: never read an account's contents until you have confirmed its identity. The items below are just

This is a submission for Weekend Challenge: Passion Edition Target categories: Best use of Snowflake...

This is a submission for Weekend Challenge: Passion Edition What I Built Loyalty Ledger — a fan loyalty tracker where your check-in streak, badges, and history live on Solana instead of some app's database. Live app: https://loyalty-ledger-blond.vercel.app Here's the problem I kept coming back to. Every sports app wants you to check in, engage, "prove your loyalty" — collect points, build a streak, unlock a badge. Cool. Except every single one of them throws that history away the second you stop opening the app. Switch apps and your streak resets to zero. Get banned, or the app shuts down, or they just quietly decide to wipe inactive accounts one day — and your history is just... gone. Because it was never actually yours. It was a number sitting in someone else's database, and they could reset it, inflate it, or delete it whenever they felt like it. You had zero say in it. And that bugged me way more than it probably should have. Like — we figured out how to make ownership portable for money, for domain names, for digital art. But "I've supported Argentina since 2019" 🇦🇷 still lives and dies inside one company's backend, and nobody's really questioned that. So I kept the weekend scope deliberately small: prove one fan's loyalty to one team, for real, end to end — instead of sketching ten features that are all half-fake. You connect a wallet, pick a sport and team, and check in. FIFA World Cup is the fully working path here ⚽ — that check-in sends an actual transaction that creates or updates a program-owned account, not a row in my database somewhere. Your streak count, your badge tier, the actual badge tokens — none of it exists anywhere I control. Which honestly felt a little weird to build, in a good way. Once that core loop worked, I built the rest of the identity around it: a Fan Passport that shows your streak, a derived "Fan Score," your tier (Rookie → Devoted → Veteran → Legend 🏆), a progress bar toward the next tier, an achievements grid with locked/unlocke

This is a submission for Weekend Challenge: Passion Edition What I Built Loyalty Ledger —...

This is a submission for the DEV Weekend Challenge: Passion Edition . What I Built Everyone will tell you about the passions they have. Nobody talks about the ones they quit. I played cricket every evening from age 11 to 17. I told everyone I'd play Ranji Trophy one day. Then the entrance exam years came, the bat went behind the cupboard, and I never went back. Eight years now. EMBER gives that abandoned passion a voice. You confess what you quit. AI forges its persona: the dusty object, the game itself, or the younger you. Then it talks back , out loud, in a voice matched to its temperament. It asks the question only it can ask: why did you really stop? Then it offers two doors: 🔥 Rekindle it. It negotiates the smallest possible first step ("Pick up your old bat and feel its weight. Sunday evening.") and you seal the pledge on-chain , where you can't quietly delete it. 🕯️ Lay it to rest. It says goodbye properly: a personal eulogy, spoken aloud, and a permanent on-chain stone. Closure is a feature, not a failure state. Every anonymized session joins the Atlas of Abandoned Passions , a live map of what humanity gives up, at what age, and what killed it. When I ran my own confession through it, the app decided my passion should speak as " Your old cricket kit bag ." Its first words: "It's been a while since you hoisted me up here, hasn't it? I still remember the thrill of a good cover drive, too." I built a thing and it emotionally wrecked me on the first test run. Working as intended. Demo 🔗 Live app: https://ember-himanshus-projects-acd54afd.vercel.app Try it in two clicks: tap an example confession (cricket at 17, the closet guitar, the novel at chapter three), headphones on. The voice is the point. A real pledge, sealed on Solana devnet: view the transaction . Code 🔗 Repo: https://github.com/himanshu748/ember How I Built It The loop is confess, converse, decide, commit, belong. Each stage is one sponsor technology doing what it is uniquely good at. Google AI (Gem