Public reading view · SmartAItomation

LinkedIn posting schedule

47 posts in the queue. The posting plan has one slot every day at 11:30 Europe/Chisinau. Only posts you schedule receive dates; the other version of a scheduled hook is an Alternative.

This is a manual publishing queue. Copying or marking done does not publish to LinkedIn.

View-only on this device. Scheduling, Done and improvements need the private editing link opened on this phone. Unlock editing

6/47marked done

Editorial score estimates draft readiness from length, example, verification step, team lesson and question. Edit it after review. “Improved” means the draft text was revised.

Hook 6

The agent called the right tool with the wrong customer ID.

Hook details

Hook 6 · Version B · Decision trade-off

The agent called the right tool with the wrong customer ID.

Score 100/100Alternative
Show postHide post
The agent called the right tool with the wrong customer ID. Should the model choose the customer ID, or should the application supply it? If the model chooses it, the agent can appear flexible. But a name, number or prior message can point to the wrong account. Prompt instructions alone are a weak boundary for a sensitive lookup. If the application supplies the identifier from an authenticated session, the agent has less freedom. That is usually the right constraint for account-scoped actions. The server can also reject any tool call that does not match the session’s permissions. The same class of error appears in a hypothetical inventory assistant that copies a warehouse ID from a prior message. Test the happy path and a request that names another warehouse. Inspect the argument before execution, the authorization result, and what the final answer reveals. A blocked unauthorized call should count as correct behavior, not as a task failure. The selection rule is simple: let the model interpret the user’s task; let trusted application code decide who the user can act for. The most important quality system is an eval suite probing account boundaries. Building it takes coached practice: define who may act, construct confusing conversations, inspect arguments and verify the result. A demo does not prove those boundaries hold. Comment “ACCESS” if you want the short guide to testing agent tool authorization. P.S. We'll start sending it once at least 10 people ask for it here. P.P.S. Connect with me so I can send it by DM after that.
Unlock to schedule Unlock to mark done

Copy post includes bold formatting when the destination supports it. Copy with bold letters uses special Unicode characters; they may be less accessible to screen readers.

Hook 40

We helped a UK startup team improve its reported RAG accuracy from 65% to 96% after a two-day workshop.

Hook details

Hook 40 · Version B · Client question answered

We helped a UK startup team improve its reported RAG accuracy from 65% to 96% after a two-day workshop.

Score 100/100Alternative
Show postHide post
We helped a UK startup team improve its reported RAG accuracy from 65% to 96% after a two-day workshop. “Can our engineers get the same result?” There is no honest way to promise that from one engagement. The metric definition, dataset and causal breakdown for that owner-supplied case are not available here. What your team can do is build a comparison it trusts. Hypothetical procurement RAG example: a parts agent retrieves the current stock record and correctly says three units are available, but omits the remaining order shortfall. Retrieval succeeded; task completeness failed. A useful eval records the expected source and both required answers, then scores evidence coverage and response completeness separately. If you automate that review with a model judge, ask domain experts to label passing and failing examples first. Inspect false passes, choose any score threshold on development cases, and leave untouched cases for the final check. After one focused improvement, rerun the same set and inspect what got worse. Keep sampling new traces because a curated offline set will not reveal every production failure. The most important part of production RAG is a team-owned eval loop. Engineers need to label hard cases, calibrate the judge and revisit false passes before users find them. That capability can serve several AI products, not just one demo. Comment “RAG” if you want the short guide to separating retrieval from answer quality. P.S. We'll start sending it once at least 10 people ask for it here. P.P.S. Connect with me so I can send it by DM after that.
Unlock to schedule Unlock to mark done

Copy post includes bold formatting when the destination supports it. Copy with bold letters uses special Unicode characters; they may be less accessible to screen readers.