Guardrails Before the Work, Acceptance After It
Handing real work to agents takes two records: what an agent may do before it acts, and who accepted what it produced afterward. OrgX keeps both on the same initiative.
OrgX / Journal
Research &
field notes.
What we learn building AI work that carries its context forward. Experiments, engineering decisions, and the evidence behind them.
Featured field note
Open standard · Jul 22, 2026
Agent work now has a receipt
Agent Work Receipt v0.1 is an open, account-free contract for portable evidence, deterministic integrity, and independent verification across agent runtimes.
OrgX4 min read
The archive
16 articles
3,328 receipts. One acceptance row.
Braintrust and Basis made agent behavior testable. The next primitive makes the judgment cumulative: an open work receipt that binds a behavior verdict to authority, artifacts, cost, and human acceptance.
Agent work now has a receipt
Agent Work Receipt v0.1 is an open, account-free contract for portable evidence, deterministic integrity, and independent verification across agent runtimes.
Memory Is Priced as a Cost. Proof Is Priced as Insurance.
Recall infrastructure tops out at $249/month. Proof gets compared against the dispute, the audit, and the cancelled project. OrgX prices like the second list.
A Benchmark Should Measure Its Own Errors
OrgX-Bench V1.2 adds solution-equivalence audits, counterfactual twins, contamination burn rules, statistical precision, and public corrections before any frontier headline can ship.
We Re-Ran the Autonomous Benchmark on Current Models
The OrgX autonomous initiative benchmark had a quiet rot problem: its judge panel pointed at models that no longer exist. We fixed it, re-ran the full catalog on current GA models, fixed a cost bug along the way, and tied the autonomy score to the gated-autonomy controls that now ship in OrgX.
Agents Do Not Need Another Issue Tracker
Linear, Jira, and Notion all expose useful MCP surfaces. OrgX is taking a different bet: the fastest agent workflow is the one where one tool call becomes durable company memory, execution state, and proof.
OrgX. The Company That Runs While You Are Away.
Continuity is the missing infrastructure for AI-native companies. OrgX is the operating system that holds the thread between people, agents, decisions, and time.
Memory is the structural lift — Phase 2 substrate benchmark
We ran 136 tasks across 4 models × 4 orchestration cells × 3 dependent task sequences. Single-shot benchmarks structurally hide what agents cannot fake: cascading context. Here is the data, the surprises, and what we changed.
The Most Underrated Product Surface in AI Is the Setup Script
The first five minutes decide whether your AI tools share company memory or become six separate rooms with six separate amnesia. That is why we built OrgX Wizard.
We Generated 75 Ad Concepts. The Useful Part Was Killing 60.
The point was not volume. It was forcing the system to find the few ideas with enough pain, specificity, and visual tension to deserve production.
Our Autonomous Benchmark Has Independent Judges Now
The OrgX autonomous initiative benchmark now publishes generated artifacts, independent judgments, token-level costs, and the failures that still need human review.
Why AI-Generated Brand Content Is Mostly Slop
AI content looks like slop when a model is asked to carry taste, memory, and QA by itself. The fix is not a better prompt. It is a content system.
The OrgX Way
Wearing many hats is not a founder superpower. It is a coordination failure wearing a flattering name. The founder should not have to be the operating system.
You Are the API Between Your AI Tools. OrgX MCP Fixes That.
I kept opening new Claude sessions and typing 'let me catch you up.' OrgX MCP is the continuity layer that stops founders from manually carrying context between ChatGPT, Claude, Cursor, and the rest of the stack.
How We Prove OrgX Works
How OrgX-Bench separates public mechanism runs from private headline evidence, measures benchmark error, and evaluates trustworthy initiative completion.