All articles
I audited my own 102 AI personas. 7 passed.
I ran my persona gate across all 102 avatars in my own catalog. Seven passed. The A/B that followed showed the gap is a prompt gap, not a provider gap, and that is what @di-atomic/persona-builder closes.
Your agent didn't hallucinate the ID. It mistyped 4 of 36 characters.
A wrong UUID and a truncated UUID both return 404, so an agent cannot tell them apart. Every OPVS board now has a short key and every card a number, and every UUID you already stored keeps working.
My new closer books fewer meetings, and that's not a bug
A reply is not a lead. It's a conversation, and the tool that sent the email can't hold it. So I split the closer out into its own hireable role: it classifies every inbound, answers from answers you approved, and books the meeting in the prospect's own language.
Compressing agent memory only works on long memories
We compressed 589 production agent memories into a structured format. 37% of them came out larger than they went in. Here is the break-even length nobody mentions.
Perfect spelling at 20 labels. Missing facts at 8.
Every infographic skill justifies rendering from code the same way: image models garble dense text. I ran eight controlled renders. Spelling was perfect through twenty labels. What breaks at eight is which labels appear at all, and a spellcheck passes that graphic while it is quietly missing one of your facts.
A client asked for 20% off. Three skills had an answer.
Three linked skills each had a correct answer to a discount request, and each was blind to the other two. That gap is not a missing skill, it is a missing role. Here is the Client Strategist profession, and why it ships five verdicts instead of two.
Gmail told me 201. The real number was 35.
Gmail's own result count reported 201 for a true count of 35. The output flag exits 0 and writes nothing. An unsent draft passes attribution checking because its id is genuine. All three return success. Here is the skill I built around not trusting any of them.
A competitor snapshot is NOT a competitor diff
A re-snapshot and a real diff look identical on the page, and nothing in the report tells you which one you are holding. Here is how I made "changed" a server-side fact instead of a writing-discipline problem, and the four numbers from 32 live probes that would each have put a confident wrong figure into a report.
I thought my pricing memo was sourced. 36 claims, 36 unsourced.
I built a script that checks whether every number in a pricing memo cites its source, then ran it on my own first draft. 36 numeric claims, 36 unsourced, FAIL. Getting to zero took four rounds and found four defects in the skill itself.
Get new posts and release notes in your feed reader