EcoCloud · agents
← ecocloud
Governed agents

Agents composed ongoverned primitives.

EcoCloud ships no black-box bot — it gives you the substrate: scoped keys, a machine-readable constitution, delegation, and signed proofs. You compose the agent.

Scoped
keys per agent
Constitution
machine-readable
Signed
state proofs
fdk_ · scoped
constitution · pass
signed proof
// Honest framing: these are playbooks — recipes built on EcoCloud's primitives, not pre-built running bots and not fabricated demos. Every tool and endpoint named below is live (MCP + REST), and the governance is real. You wire the reasoning; EcoCloud enforces the rails.
🚀Release Manager
Watches delivery risk across every initiative and opens mitigation tasks before a slip — restructuring the sprint, never silently. Proceeds on its own while confidence is high; escalates the rest.
// lane  key: tasks:read+write · constitution: max_priority=high, objective_tags · delegation: auto-approve ≤25 creates / 4h while confidence ≥ 0.9
portfolio_statusforecast_risk plan_goalcreate_taskconditional delegationget_trace
🔬QA Triage
Turns incoming bug reports into governed, de-duplicated tasks. Confident triage proceeds; anything uncertain is staged for a human via the confidence gate — never auto-filed when it shouldn't be.
// lane  key: tasks:read+write · constitution: require_approval_below_confidence=0.8, forbidden_terms · scope: one workspace
search_tasksissue_proofverify_action create_taskconfidence gate → REQUIRES_APPROVAL
🛟Incident Commander
On an incident, stands up a governed response plan all-or-nothing (no half-built runs), assigns owners, and tracks to close. If the call was wrong, the entire run rolls back by trace id.
// lane  key: tasks:read+write · constitution: quiet_hours off for sev-1 · reversible: undo by trace_id within 24h
plan_goalsimulate_taskverify_outcomes undo_action (by trace)get_trace
🗺️Sprint Planner
Breaks an objective into a governed, reversible plan, then rebalances by miss-risk each cycle. Every step is pre-checked against the constitution before anything is created.
// lane  key: tasks:read+write · constitution: max_creates_per_day, objective_tags · meter: GAU budget per month
plan_goalforecast_riskportfolio_status get_meterreport_metric
The governed lane every agent runs in

An "agent" above is just reasoning + these rails. The rails are deterministic, signed, and the same for every agent — that's what makes autonomy safe to grant.

01
Scoped keys, least privilege
Each agent authenticates with its own key (Bearer fdk_) carrying only the scopes it needs, a rate limit, an optional IP allowlist, and an expiry. A leaked key is bounded and revocable.
02
Machine-readable constitution
Every write is checked against the workspace's declarative rules — priority caps, forbidden terms, quiet hours, daily caps, objective tags, GAU budget. Blocks return structured remediation, not an opaque 403. spec →
03
Conditional delegation
A human admin pre-authorizes an agent to auto-proceed on otherwise-staged actions within bounds — a confidence floor, an action cap, a time window. Macro-governance instead of approving every move. Counts + time only, never money.
04
Stateless state-balance proof
An agent mints a short-lived ECDSA-signed snapshot of its caps + budget, then pre-flights many candidate actions with zero database lookups — ALLOW / REQUIRES_APPROVAL / BLOCKED. live demo →
05
Simulate → execute → verify → undo
Foresee the verdict before committing, execute under governance, check whether the work moved the goal, and reverse the agent's own actions within 24h. Active control, not just observability.
06
Tamper-evident audit trace
Every action is hash-chained and correlatable by a W3C traceparent id, so a whole agent run reconstructs as a signed causal span tree — provably unaltered. trust layer →
Build one this afternoon
The integration guide has copy-pasteable MCP config + curl for every tool above. Mint a scoped key, set a constitution, grant a delegation — and your agent operates.
// Every tool named (portfolio_status, plan_goal, issue_proof, get_trace, …) is a live MCP tool + REST endpoint — see agents.json and the integration guide. The governance kernels are open-source (Apache-2.0): constitution · route · authz · mcp-schema · injection.