Jason Cousins

Building SnapSpace: Governance for AI agents

[Jason Cousins @Agent_invariant]

@hthieblot Building governed drone systems that stay autonomous through C2 link drops and recovery.

[Jason Cousins @Agent_invariant]

k6 load test on SnapDesk.
1,000 concurrent VUs across 4 workers.
1,070 req/s. 133,662 requests. 0 failures.
All on a 2-core ThinkPad T480s.
p50 250ms. p95 1.4s. p99 4.48s.
SnapSpace wasn’t the bottleneck. The Node event loop hit its ceiling first. Then the Neon connection pool became the next constraint under higher load.
The deterministic control layer held. Scaling limits showed up in the surrounding runtime: not the kernel itself.

Testing in public.
Dropping ad we go

[Jason Cousins @Agent_invariant]

@sesigl Glad you agree. Thats just what we are working on
https://t.co/1oZIloxWlN if you get 5 mins take a look

[Jason Cousins @Agent_invariant]

@sesigl I'm treating the model as the proposal layer, not the commit layer. It can generate all it wants, but the part that validates, enforces policy, handles retries and blocks duplicate execution sits outside it. Simple reliability without pretending prompting is control.

[Jason Cousins @Agent_invariant]

@hthieblot Governance.

https://t.co/1oZIloxWlN

[Jason Cousins @Agent_invariant]

@boardyai Ok. Make it happen!

[Jason Cousins @Agent_invariant]

@DStrachman Yes thats the fix. Thanks

[Jason Cousins @Agent_invariant]

@WorkflowWhisper This is the exact gap I am building for now. In my workflow it wouldn’t keep running. It would detect the output drift, hold downstream action, route it to escalate or buffer state, & alert a human before processed. Running is not the same as governed.

https://t.co/1oZIloxWlN

[Jason Cousins @Agent_invariant]

Test 21: SnapSpace under live pressure at scale.Governed agent execution, deterministic decisions, hard boundaries between intent and action, full replayable audit. 8-phase proof + 25-wave 200-desk monster gauntlet. Zero failures. Details in the video.

[Jason Cousins @Agent_invariant]

Test 21: SnapSpace under live pressure at scale.Governed agent execution, deterministic decisions, hard boundaries between intent and action, full replayable audit. 8-phase proof + 25-wave 200-desk monster gauntlet. Zero failures. Details in the video.

[Jason Cousins @Agent_invariant]

@WorkflowWhisper Yes. Silent failure is really untracked human substitution. If you cannot prove a workflow ran, failed, or escalated, you do not have automation. You have hidden labour wearing an automation mask.
https://t.co/1oZIloxWlN

[Jason Cousins @Agent_invariant]

@GG_Observatory I don’t ledger every micro-decision. Instead, ledger governed commit points, state transitions, and replay-critical facts. High-frequency local reasoning stays ephemeral or gets compacted into deterministic summaries. The boundary is the product.
https://t.co/1oZIloxWlN

[Jason Cousins @Agent_invariant]

@GG_Observatory Full history is not context, it’s contamination. Handoffs need governed state, explicit intent, and a clean commit boundary. Otherwise one bad route poisons every downstream agent.
https://t.co/1oZIloxWlN

[Jason Cousins @Agent_invariant]

Test 21: SnapSpace under live pressure at scale.Governed agent execution, deterministic decisions, hard boundaries between intent and action, full replayable audit. 8-phase proof + 25-wave 200-desk monster gauntlet. Zero failures. Details in the video.

[Jason Cousins @Agent_invariant]

Test Environment.
Test 20 Jury Rule Collision
(Deterministic Precedence Guard)
Verification that the Jury Layer resolves overlapping valid rules into one stable verdict.

[Jason Cousins @Agent_invariant]

@ageisf42 @Cloudflare Agreed! Tool use is the 'easy' part.
The real system is identity, policy, commit boundaries, and replayable audit. Without a jury-governor layer between intent and execution, agents are just unsupervised speed with a nicer UI.
https://t.co/1oZIloxWlN