Lean Agents: Decide What Your Agent Can Reach Before It Runs

·12 views

Every tool you connect to an agent is two things at once: tokens the model reads on every run, and an action the model can take. So the same inventory answers your cost question and your permission question. I start every agent with that inventory, and with nothing connected that the task doesn't need. I talked through this with Tom Smith on CoderLegion's Developer Stories (video, from 9:46). This post is the practical version.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Multimodal AI Breaks at the Tokenizer, Not the Model

TL;DR — The gap between a multimodal demo and a production system isn't model capability — it's the token economics of turning video and audio into sequences the transformer can read. Naive frame sampling and fixed-window audio chunking quietly blow up cost, latency, and accuracy long before the language model does any reasoning. Treating modality ingestion as a retrieval problem, not a context-stuffing problem, is the fix most teams skip. Every multimodal demo follows the same script: drop in a short clip, ask a question about it, watch the model nail it. Then someone tries it on a forty-minu

0 comments Read more at DEV Community

ProgrammingDEV Community ·

OfferProof: an offline job-scam checker for my fresher friends

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend When I read "build for a friend", my first thought was that none of my friends had a problem I could fix in a weekend. Then I thought about what most of my batch is doing right now. We're all applying for our first jobs. And if you're a fresher looking for a job, you're exactly who fake job offers are aimed at. They look something like this.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Your Agent Said "Done". The Filesystem Disagrees.

"Task completed successfully." That's the most common lie in agent systems. Usually the agent isn't lying on purpose. It just reports what it intended to do, the logs repeat it, and nobody checks the filesystem. I built VASB (Verifiable Agent Systems Benchmark) to make that failure measurable. It grades what actually happened to the world, not what the agent said happened.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How to know when a dependency changes your day

Watching every release is not monitoring. It is a second inbox with a package name on it. Open your package.json. Count the direct dependencies. Now multiply by roughly one release every few weeks, and you have the number of events per year that a tool watching your dependencies could send you.

0 comments Read more at DEV Community