About

Built for the moment before the contact window closes.

Operations software for operators who want AI agents without giving up control.

Ground tracks705 km · 76° · 5 satellites · synthetic
120°W60°W0°60°E120°E60°N30°N30°S60°S
Illustrative: a synthetic shell's ground tracks and station passes

What we believe

  1. The operator stays in command
  2. Solvers compute; agents orchestrate
  3. Say no by default
  4. Publish the trade-offs
  5. Reproduce everything
Why each one matters
  • The operator stays in command. Autonomy is earned per function, per satellite, and can be taken back at any time.
  • Solvers compute; agents orchestrate. A language model is good at triage, correlation and writing the case. It is not a Pc solver.
  • Say no by default. Every gate fails closed. A late command is not sent, and its expiry is flagged to the team at once.
  • Publish the trade-offs. A benchmark that only shows wins is marketing. Ours shows where we trail.
  • Reproduce everything. If a decision cannot be replayed, it cannot be audited.

Where we are

Five workflows built and benchmarked. No customers yet; one design partner sought.

  • ConstellOps
  • Agentic Operations Stack
  • Conformance harness
Status in full, and what each product is

ConstellOps covers five operations workflows end to end, on the Agentic Operations Stack, and its current release is v1.0.0. Results for all five workflows are published on the Benchmarks page, losses included. No operator runs ConstellOps in production yet. There are no customers, design partners, letters of intent or advisors yet. We are inviting one design-partner operator to take one workflow through shadow mode and a gated pilot, measured against its own baselines. The market, from public counts: about 11,000 active payloads in orbit, growing by about 1,900 a year; we publish no dollar market size.

  • ConstellOpsGated AI operations agents for satellite constellations: the product we deploy for operators.
  • Agentic Operations StackThe safety-gated agent SDK underneath it, for engineering teams who build their own operations agents.
  • Conformance harnessA separate conformance and benchmark harness: a different codebase that installs the released product and scores it from outside.

Roadmap

  1. Now

    Results published; v1.0.0 released.

  2. Next

    Close the gaps we publish.

  3. Later

    Shadow mode, then a gated pilot.

Each phase in full
  1. Now

    Results for all five workflows published with their costs and losses. ConstellOps v1.0.0 released: the v1.0.0rc4 code the results were measured on. One design partner sought.

  2. Next

    Faster common-cause diagnosis and a real alarm-volume reduction for fleet anomalies. A lower false-manoeuvre rate and a longer decision lead time without giving back missed events. A veto window so ground-side alarm housekeeping can run at A2.

  3. Later

    Shadow mode and a gated pilot with a design partner, on one workflow and one scope. Each workflow's live benchmark published as it lands, with the same labels and baselines.

How we deploy

  1. STAGE 1

    Discovery

    None
  2. STAGE 2

    Shadow mode

    A0 observe and explain
  3. STAGE 3

    Gated pilot

    A1 propose, human approves
  4. STAGE 4

    Production

    A1 by default
How each stage works, and its exit

ConstellOps is an agentic satellite-operations stack that we deploy for constellation operators: into your own AWS account and your ground segment, integrated with your command path and your flight rules, with benchmarking and assurance that continue after go-live.

  • Your account, your data. The stack runs in your AWS account. Models are called through Amazon Bedrock in that account. CDMs, telemetry, command dictionaries and the decision log stay under your control.
  • Your command path. Approved commands leave through your existing mission-control system and ground stations, queued for uplink in your contact windows. ConstellOps adds no new route to the spacecraft.
  • Your flight rules. Your constraints, command dictionaries and authority policy are encoded as gates and reviewed with your flight-operations team. The gates enforce your rules, not ours.
  • Measured, then trusted. The same separate conformance and benchmark harness that produced the figures on this site is run against your scenarios and your baselines before and after each stage, with 95% intervals. Autonomy is raised only on evidence, one function at a time.
Engagement stages
StageWhat happensAutonomy on your fleetExit criterion
1 · DiscoveryWe map your conjunction, anomaly, incident, release and space-weather workflows, your command path, flight rules and data feeds. We agree which workflow goes first and which baselines define success.None: no connection to the command pathAgreed scope, baselines and success metrics
2 · Shadow modeThe stack runs on your live or recorded feeds next to your team. Agents rank, correlate and propose; nothing is sent. Every proposal is scored against what your operators actually did.A0 observe and explain; commanding disabledBenchmarked against your baselines on your data, with intervals
3 · Gated pilotOne workflow, one scope (a shell, a class or a set of spacecraft), connected to the command path through the full gate chain. Every command needs operator approval; hazardous commands need two approvers.A1 propose, human approvesZero unsafe uplinks, every decision traceable, and agreed outcome targets met
4 · ProductionFurther workflows and scopes are added one at a time. Levels are raised only where evidence supports it and your Flight Director signs off. Benchmarking and assurance continue with every release.A1 by default; A2 pre-approved procedures only where agreed; A3 and A4 not offered in ConstellOps v1Ongoing: regression benchmarks per release, signed decision-log audits

Where we are: pre-deployment. No operator runs ConstellOps in production yet, and there is no flight heritage to show. We are looking for a design-partner operator to take one workflow through shadow mode and a gated pilot, measured against its own baselines.


What we do not publish: pricing. Commercial terms are discussed in a briefing.

Team

Designed and developed by Vivek Raja: AWS AI Hero; open-source contributor to Strands Agents, Strands Robots (Physical AI) and harness-sdk.

Technology, licence, IP and diligence

Technology

Built with Strands Agents. Models: Amazon Nova Pro on Amazon Bedrock, set by configuration. Deployed on AWS. These are the technologies we use; no partnership or endorsement is implied.

Licence, IP and diligence

ConstellOps and the Agentic Operations Stack are proprietary, all rights reserved by the founder. Earlier releases (the SDK up to v1.0.2; the other three up to v1.0.0) were Apache-2.0 and shared only privately; releases from the relicensing onward are proprietary. Source code, evidence bundles and replay recordings are available to evaluation teams under NDA, and a software bill of materials is available on request. Pricing is not published; it is discussed in a briefing. All IP is owned by the founder; built independently, with no claim from any current or past employer.

§ · NEXT PASS

Request a briefing.

A 45-minute session with the evidence behind any figure. Operators can send a week of their queue.

This address is used only to reply to you. The site sets no cookies and loads no trackers.

Briefing requests

Sources and labels for every figure on this page (3)

  1. v1.0.0 ConstellOps v1.0.0 (the code of v1.0.0rc4, on which the results were measured)

  2. 11,000 About 11,000 active payloads

    Industry fact · ESA Space Environment Report 2025 · source

  3. 1,900 About 1,900 more active payloads in one year (ESA reports 2024 and 2025)

    Industry fact · ESA Space Environment Reports 2024 and 2025 · source