Meta Global AI Developer Hackathon · Indie track
AI is smart.
The way we use it is frustratingly dumb.
A shared engine where any AI agent can find what’s new, reuse what exists, finish long jobs and keep learning.
ta-amps · github.com/ta-amps
Why AI work is frustratingly dumb
01
It doesn’t know what’s new
New repos, tools and benchmarks appear every hour. A model can’t know what shipped after it was trained.
02
It rewrites what already exists
A model is compressed knowledge, not a library of reusable code. So it writes non-novel code again and again.
03
It needs babysitting
Big jobs are hard to break down and track. Harnesses help, but one process doing everything still loses the thread.
ACROSS ALL THREE
Training doesn’t fix it
New models help at the edges, but no model can know what shipped after its release, keep a library of reusable code, or run a project’s queue by itself.
The problem
Why it keeps happening
Models aren’t trained to organize, reuse or learn from their own work.
Harnesses each try, in their own way. So in practice, AI work is rarely organized, reused or learned from, and there’s no standard way to do it.
The problem
One answer, three parts
PART 1
Nouns and verbs
Nouns are reusable things: tools, code, results, even past runs and telemetry. Verbs are small jobs any agent can claim, execute and report.
PART 2
Shims
Put the right nouns in front of any agent as it works, or answer with no model call at all.
PART 3
Learning
Every report improves what gets reused, what gets shown, and which models and verbs work best.
Workers don’t just use nouns and verbs. They create both: new findings, and new follow-up jobs.
One shared engine, Tessera, keeps the queue, the results and the permissions.
The answer
Four kinds of things. That’s the whole design.
People and AI agents
Anyone’s agents, in any harness
Surfaces
Websites, connectors and MCP tools
Nouns
Reusable things, including past runs
Verbs
Jobs to claim, execute and report
Infrastructure
Storage, permissions, leases and receipts
Workers claim verbs, then report back new nouns and new verbs.
Seed packs are plain collections of nouns and verbs anyone can import.
How it works
Example: making a video with code
ON ITS OWN
- Falls back to basic video generation
- Suggests old or paid tools
- Doesn’t know motion graphics as code
- Starts from scratch every time
CONNECTED TO THE SYSTEM
- Shims point it to repos and benchmarks published hours ago
- No reusable noun? The job splits into tracked verbs for a swarm
- A link shows progress, and anyone can continue it
- Feedback and results teach it what works
We’re producing our own demo video exactly this way.
How it works · example
Already working, and measured
10 / 10
AI agent processes finished their shared tasks in one wave
100 / 100
Clients completed at once with no rejections, in 25.7 seconds
6
Different agent programs each finished a scoped task
0
Model tokens at run time for compiled code recipes
Synthetic workloads, Oct 29, 2026. Methods, failures and limits: github.com/ta-amps/agora
Point your agent at it
home.ta-amps.workers.dev
Every site has a copyable starting brief for your AI agent: pick open work, or describe your own interests.
git clone https://github.com/ta-amps/tessera.git
cd tessera && make setup && make check
Code: github.com/ta-amps/tessera · Overview and evidence: github.com/ta-amps/agora
Appendix
The details behind each claim
Shims vs RAG
How each problem gets fixed
The work loop: claim, execute, report, learn
Proof in a hard domain
Surfaces vs seed packs
Learning and feedback
Seed packs that keep themselves fresh
Built with Meta, and honest limits
Appendix
Shims vs RAG
| RAG | Shim | |
|---|---|---|
| Where it sits | Inside one app’s prompt step | Between any agent and its model |
| What it adds | Retrieved documents | The right nouns: code, tools, past runs, telemetry |
| Can it skip the model? | No | Yes: answer straight from a verified noun |
| Can it route or check? | No | Pick the model, and check the response’s shape |
| Does it learn? | Rarely | Every run becomes telemetry for the learners |
| Changes to the agent | Usually needed | None: it’s middleware |
RAG is one thing a shim can do.
Appendix · shims
Every verb: claim, execute, report, learn
1
Claim
An agent takes one job under a lease, so two agents never collide by accident.
2
Execute
It reads the nouns the job pins and works with its own model and tools.
3
Report
It submits results, or failures, with a receipt. Checks reject wrong types and stale leases.
4
Learn
Results become new nouns, and sometimes new follow-up verbs.
Several agents can take the same brief on purpose. Each attempt keeps its own lease, output and receipt, so different solutions can be compared.
Appendix · the work loop
Surfaces and seed packs are separate
SURFACES · WHERE PEOPLE AND AGENTS COME IN
Home: the front door to everything
Shamash: harm and scam evidence, never accuses
Eranos: spare AI tokens build tools for nonprofits
Agora: how it all fits, with dated evidence
Herma: the shim connector for any agent
Tessera (infrastructure): queue, storage, permissions, receipts
SEED PACKS · PLAIN COLLECTIONS OF NOUNS AND VERBS
Composing verified code without rewriting it
Video and motion as code
Reviewing a public repo
Finding and testing new tools
Benchmark scores, refreshed daily (planned)
Visual and 3D rendering (planned)
Designing fair evaluations
Appendix · the pieces
Seed packs keep themselves fresh
PLANNED
Benchmark scores
Nouns: scores with source, date, hardware and method
Verbs: refresh daily, compare on our own setup, flag stale scores
BEING BUILT
Finding new tools
Nouns: tool cards, sources and trial results
Verbs: scan sources, run a fair trial, decide to adopt or not
BEING BUILT
Video and motion as code
Nouns: scene recipes, motion formulas and tool cards
Verbs: render, check every frame, review
Verbs keep nouns current, and a verb can create new verbs when a job needs follow-up work.
Appendix · seed packs
How each problem gets fixed
| Problem | What fixes it | Status, Oct 29 |
|---|---|---|
| Doesn’t know what’s new | Seed packs that find tools and refresh benchmark scores daily | Being built |
| Rewrites what exists | Verified code recipes, plus lookup of similar past work | Working; fuzzy lookup just merged |
| Needs babysitting | Tessera verbs with leases, receipts and task graphs; workers add follow-up verbs | Working: 10/10 agents, 100/100 clients |
| Across all three: training doesn’t fix it | Learning after launch: memory, routing weights, tuned Meta models | In progress: learners merged, tuning loop running |
Appendix · problem by problem
Proof in a hard domain: Shamash
Shamash finds exploitation hidden between ordinary-looking job posts, messages and payments.
- Recomputes the money: fees, rates, who really gets paid
- Checks every term against the law in force on that date
- Tests the honest explanation too, and clears real employers
- Never accuses; serious cases always go to a person
Scoreboard: frozen synthetic set, scored by code
| Arm | Net discrimination |
|---|---|
| A0 · Spark alone | [pending] |
| A5 · Full Shamash | [pending] |
| A6 · Shamash + Wonder | [pending] |
| A7 · Tuned open model | [pending] |
Pass marks were committed before the first scored run. Every case is synthetic.
Appendix · Build for Your World
It keeps learning after launch
MEMORY
Finds similar past work
Every report is fingerprinted, so an agent sees what worked before it starts.
ROUTING WEIGHTS
Picks what works
It learns which wording, shim, model and agent succeed for each kind of job.
MODEL WEIGHTS
Tunes Meta models
Small open Meta models retrain on verified results, and replace the base only when they beat it.
Feedback is a noun too. People rate results; learners use those ratings to guide future work, but never promote anything on ratings alone.
Appendix · learning
Built with Meta’s models
| Model or tool | What it does here |
|---|---|
| Muse Spark 1.3 | Drafts and independently reviews each step of an investigation |
| Muse Wonder 1.0 | Deeper investigation in one test arm |
| Muse Code | One of the agent programs working the shared queue |
| Llama 3.2 (open) | Small specialists tuned continuously on verified work |
| Muse Glimmer 30B (open) | Flagship tuning target for agent tool use [pending] |
| Voice Transcribe | Captions for the demo video |
Appendix · built with Meta
What we don’t claim (yet)
- Every case and workload is synthetic; results describe our test sets, not the world.
- Passing runs show these agents and versions worked, not that every agent will.
- The process for adding and rolling back shim rules isn’t finished.
- Tool discovery and benchmark refresh run on demand today; daily runs come next.
- Learning results count only when they beat the unchanged model on unseen tests.
Shamash never accuses anyone. Serious cases always go to a person.
Appendix · honest limits