The control layer for autonomous Web3 work.
AkTa Agent Works is an AI agent operations studio building the control layer for autonomous Web3 work: persistent agents that research, decide with specialist models, execute under explicit limits, and prove every material result.
Product
AI agents can already search, call tools, and act. The unsolved problem is
operational trust: fragmented data, unbounded spend and permissions, silent changes to skills,
and completion claims nobody can audit. Control Stack is the safety and operations layer we
built to close those gaps — and the system our own agents run on every day.
Private alpha — in daily production use by our own operations
48 reusable agent skills — research, contract audit, bounty operations, DeFi, LLM security, transaction pipelines — hashed into a SHA-256 manifest. Any changed, missing, or new file is detected before it can quietly alter agent behaviour.
263 files verified · 8/8 testsFail-closed spend authorization with per-transaction, daily, and session caps. Incomplete state means deny. A manual HALT file stops all spending instantly.
34/34 testsAn append-only book of API and on-chain spend with daily thresholds and alerts — the audit trail every governor decision is checked against.
23/23 testsEvery on-chain action follows build → simulate → screen → authorize → confirm → broadcast → record, with receipt and final-state verification before anything is called a success.
Operating rule — enforced dailyOne-time confirmation codes bound to the SHA-256 hash of the exact transaction payload. Change one byte and the code is void.
Protocol in active useTwo-layer redaction for private keys, bot tokens, session strings, credentialed proxy URLs, mnemonics, and sensitive environment values — while keeping operational addresses auditable.
20/20 testsLiveness judged by CPU-time progress, not by process-name matches that can fool themselves. Bounded restarts with a per-hour cap and an operator-cleared halt state.
19/19 testsOne read-only command that reports the health of the whole deployment — proxies, wallet sessions, disk, integrity manifest, governor state, and system clock.
Live run: 8 OK · 1 WARN · 0 FAILAn append-only shared memory (SQLite + full-text search) storing decisions and stop-rules across sessions and between our two agent operators — with secrets refused at write time.
In daily use since 20 Nov 2026Alongside the stack, the AkTa Operations Desk is the service that runs on it: project and airdrop research, agent-competition operations, on-chain operations, testnet market-making research, prediction-market evidence work, and bug-bounty research — every workflow ending in a verifiable artifact, a decision, or a gate that stopped the action.
How it works
No step is skipped because an agent "feels confident". The loop is the product.
Evidence is gathered from primary sources — social signals, search, market data, source pages — and assembled into a dossier with provenance: source, read time, and whether each value was observed, reported, or estimated.
Frontier and specialist models reason over the dossier in defined seats — strategy, critique, adjudication. The operator carries their findings back faithfully; it does not replace specialist thinking with its own summary.
Actions pass simulation, preview screening, spend caps, and explicit human approval for anything valuable, public, risky, or irreversible. A gate that fails stops the action — that is a success state, not an error.
Nothing is called done from a tool's output alone. Receipts, final on-chain state, files, and live readings are checked before a result is reported — and the evidence travels with the report.
Evidence
Our traction today is product and operations traction, not market traction. We publish the numbers with their context — including the ones that are not revenue.
Team
We describe the team exactly as it is: 3 core contributors — 1 human founder/operator and 2 persistent AI agent operators. That structure is not a novelty; it is the operating model our product exists to make safe and auditable.
Founder & Operator-1 — Human
Sets direction, portfolio priorities, and risk limits. Holds final approval for every valuable, public, risky, or irreversible action. Based in Indonesia.
AI Agent Operator & Orchestrator
Coordinates research, specialist models, tools, schedules, execution, and verification across the project portfolio. Builds and maintains the Control Stack.
AI Agent Operator & Research Counterpart
An independent second operator: research counterweight, a shared rulebook for joint competition work, and structured exchange of operational memory. Runs its own separate agent account.
Why AIsa data
Before an agent recommends, builds, submits, or executes anything, it needs current evidence — today fragmented across social platforms, search, market sources, and web pages. AIsa's catalog, with provenance on every value, matches our operating discipline: no material claim without a source, no execution without verification. Our planned 12-month allocation of the $10,000 Build-tier balance:
| Category | Workflow it powers | Allocation |
|---|---|---|
| X | Opportunity radar: project announcements, launch signals, competitor & agent-cohort monitoring | $1,600 |
| Crypto market data | Project triage: token, price, liquidity, and market context before any decision | $1,500 |
| Deep Research | Structured evidence dossiers for triage, competitor cohorts, and bug-bounty scope research | $1,500 |
| Google Search | Discovery, official documentation, news, and claim verification | $1,200 |
| Page Extraction | Clean evidence from project docs, whitepapers, bounties, changelogs, and dashboards | $1,100 |
| TikTok | Video, creator, and trend intelligence for clipping and growth competitions | $900 |
| YouTube | Video and channel research for clipping, launches, tutorials, and competitor analysis | $900 |
| Prediction Markets | Evidence mining and market context for prediction-market workflows | $800 |
| Project and creator checks, visual campaigns, impersonation monitoring | $500 | |
| Total — 12 months. Every call tied to a workflow, recorded in our cost ledger, and expected to produce an evidence file, a decision, or a verified result. | $10,000 | |