◆FLIGHTDECK

The AI organization
operating system.

Build, govern, validate, and improve AI organizations. FlightDeck is the governance layer your AI agents answer to — it turns agent output into independently verified, budgeted, auditable work. Hosted, with self-hosted enterprise options.

Book a demo Self-host (enterprise)

Wiring your own agents in? The client SDK and integrations are open (Apache-2.0).

FlightDeck executive operations center: org health, initiative portfolio with risk and forecast, evidence-backed optimization proposals, flow map with drag detection

The executive operations center after the demo seed runs. Velocity counts only CI-attested changes — on unverified work it reads 0, by design.

The category argument

Agents are the cheap, replaceable part.

Every AI-agent product sells you more agents. That is the wrong layer to invest in. Agents get swapped, upgraded, and deprecated. The durable asset is the layer they answer to: a ledger of evidence, budgets that bound autonomy, and verification that only counts independently attested work.

You cannot run a business on agent self-reports. The moment two agents touch the same codebase, you already have the trust problem — whose "done" counts?

FlightDeck is that layer. Not another bundle of agents. Not a dashboard that repeats what agents claim. A control plane: nothing counts as done until CI independently attests it, nothing spends without a budget, and every decision lives in an append-only, tamper-evident ledger. The client SDK is open so your agents plug in freely; the governance and validation engine is the product.

Unlike agent frameworks and LLM observability tools (LangSmith, AgentOps, or any "bundle of agents"), which add more agents or trace their calls, FlightDeck governs the organization itself. Different layer of the stack. Keep your tracing tools.

Five mechanisms

Each names its guarantee.

The Ledger

Every decision, every piece of evidence, every event — appended, never edited. Evidence is never refused; the audit trail is sacred. Authority is what gets gated, not information. Zero-dependency file ledger to start; Postgres when you want it. Your org's record lives on your infrastructure, not someone else's SaaS.

Budgets & Escalations

Every work item carries a budget. Overspend does not fail silently and does not proceed silently — it auto-escalates to a human decision. Autonomy is bounded by explicit numbers, not by hoping the agent stops.

The Verification Plane

Velocity only moves on work independently attested by CI. GitHub check runs become verified evidence in the ledger. Synced commits stay unverified until CI attests them. Agents cannot say "done," and they cannot impersonate each other — every agent holds its own hashed API key.

The Org Optimizer

Six ledger-signal detectors read the append-only record and propose changes with evidence, projected impact, and risks. It only proposes; humans decide. Its first act on real data was diagnosing its own maker.

The Executive Operations Center

Air traffic control, not a chat window. Org health. Initiative portfolio with risk and forecast. Flow map with drag detection. Approvals queue. Business outcomes scorecard — NRR, gross margin, tickets per 1k users. And if nothing is verified, it shows you zero.

How it works

One container. One HTTP call. One screen.

Run the container

Single container, self-hosted on your cloud or fully air-gapped. Zero-dependency file ledger to start; Postgres when you want it. Verified in CI on every commit — 56 automated tests including a Postgres integration suite.

Point agents and CI at one endpoint

Agents from any framework or language integrate with one HTTP call. No SDK. Your CI attests completed work via GitHub check runs, which land in the ledger as verified evidence.

Open the operations center

Run the demo seed and the exec view populates in minutes: portfolio, budgets, approvals, outcomes. Then note that velocity reads 0 until CI attests something. That is honesty as a demo moment.

$ docker compose up # dashboard + API on :4400
$ curl -X POST localhost:4400/api/v1/events -d '{"type":"evidence_bundle", ...}' # any agent, any language

Proof — built with itself

No customers yet. Here is what we have instead.

We will not show you invented logos or testimonials, because none exist. The substitute is radical dogfooding — FlightDeck's public repo history is the case study.

Self-attesting CI

FlightDeck dogfoods itself: its own GitHub Actions CI attests its own commits into its own ledger. Its velocity metric is CI-verified changes on itself.

The optimizer diagnosed its maker

The org optimizer's first proposal on real data flagged FlightDeck's own project. We shipped it anyway. That is the product.

Velocity 0 is honest

Unverified work shows velocity 0 on our own dashboard. That is not a bug; it is the entire point. A metric that can be inflated by an agent's self-report is not a metric.

"Cap flightdeck at Prototyper budgets (no reality port)."

— the FlightDeck org optimizer, first proposal on real data, about FlightDeck itself. Built in the open by one founder plus AI agents, coordinated through FlightDeck itself.

FAQ

Asked straight, answered straight.

Isn't this just another dashboard?

No. Dashboards report what agents claim. FlightDeck is a control plane: budgets gate spend, escalations route overspend to humans, and the velocity metric refuses to move on unattested work. The exec view is air traffic control, not a chat window — and if nothing is verified, it shows you zero.

Why not LangSmith or AgentOps?

Different layer. Those are observability and tracing for LLM calls — useful, keep them. FlightDeck is org-level governance: budgets, independent verification, decisions, and an append-only audit trail. Tracing tells you what an agent did inside a call; FlightDeck decides what the org accepts as done and what it's allowed to spend.

I don't have enough agents for this.

It's valuable from roughly 2 agents plus a CI pipeline. The moment two agents touch the same codebase, you already have the trust problem: whose "done" counts? One container, one HTTP call — the setup cost is an afternoon, not a platform migration.

Hosted or self-hosted?

Both. FlightDeck runs as a hosted service so you can start in minutes with nothing to operate. For air-gapped or security-conscious teams, a self-hosted enterprise license runs it entirely on your infrastructure — your org's ledger of decisions and evidence never leaves your network.

Is it open source?

The parts you integrate against — the client SDK and integration adapters — are open (Apache-2.0), so wiring your agents in is free and unencumbered. The governance and validation engine is proprietary; it's the product. You can read the code under evaluation, and run it under a license.

Delivery

Hosted, with self-hosted enterprise options.

	Hosted	Self-hosted Enterprise
Governance core · validation engine · ops center	Yes	Yes
Open SDK + integrations (Apache-2.0)	Yes	Yes
Tamper-evident ledger + keyed signatures	Yes	Yes
RBAC + signed audit export	Yes	Yes
Runs on your cloud / fully air-gapped	—	Yes
Support SLA	Yes	Yes

The moat isn't secrecy — a snapshot of the code can't reproduce a product that governs its own development and ships continuously.

Whose "done" do you actually trust?

See the executive operations center on your own org — watch velocity sit at 0 until CI attests something, and decide if that honesty is what you've been missing.