Autonomous mission intelligence.
The category we are building toward, the evidence it stands on, and the reference mission that forces the whole problem.
The category
Autonomous mission intelligence is the software layer that lets a mission composed of many autonomous components (planners, controllers, learned perception, fault management) behave as one governed system, defined by five properties: authority, uncertainty handling, resource feasibility, safety, and evidence.
Those five properties are the definition, not any specific technique: authority (human intent is preserved), uncertainty handling (belief is first-class), resource feasibility (constraints are joint), safety (nothing runs without a permit), and evidence (every decision is replayable).
It is a systems layer, not a model. The agencies have named the same gap in their own language, as trustworthy autonomy and as assurance for autonomy. Autonomous mission intelligence is our name for the layer that closes it.
Evidence first, architecture second.
Every position on the site traces to something we can point to: NASA's ranked technology shortfalls, JPL flight heritage from Remote Agent to Ingenuity, defense solicitations, and agency roadmaps from four continents. We collected that evidence before we drew the architecture, and we keep collecting it after.
A worked example. In NASA STMD's Civil Space Shortfall Ranking of July 2024, which asked the aerospace community to rate 187 shortfalls, the entry on establishing trust and certifying the trustworthiness of autonomous systems ranks 33rd. The gap we are building into is one the community itself placed in the top fifth of everything it said was missing.
NASA STMD shortfall rankings. JPL mission autonomy papers. DARPA and DIU solicitations. ESA and JAXA roadmaps. ISRO and iDEX release notes.
Adversarial verification. Every claim is checked against its primary source by independent review before it ships, and a claim that cannot be confirmed does not ship.
Every architectural claim is a falsifiable hypothesis. When evidence refutes a position, the position moves, not the evidence.
A long-duration planetary surface campaign.
We designed the runtime against the scenario that forces the whole problem: a multi-year surface campaign with a rover, an aerial scout, and a set of distributed instruments; intermittent Earth communications on a light-second scale; compound failures; a science plan that changes as the mission finds what it finds.
Every subsystem the runtime touches, belief state, plan repair, coordination under intermittent links, learned perception with operating-domain contracts, the assurance kernel that survives a radiation event, has to work in that scenario. If it works there, defense satellites and commercial constellations become an easier problem, not a harder one.
Systems designed against slogans get built around edge cases nobody stress-tests. Systems designed against a specific mission get stress-tested from the first week. A reference mission is a discipline, not a customer.
How we publish
We publish research notes with a fixed structure, position, evidence, mechanism, open questions, references, at /writing. Every essay carries a named human author, a date, and a bibliography drawn from the primary sources. We publish when the work is ready, not on a schedule.