Tag feed

#agents

684 posts16 followers

Trending tags this week

AAArchitects Assembleblog.syncyourcloud.io

AWS Bedrock AgentCore Payments: What Your Infrastructure Needs Before You Connect

3h ago · 11 min read · AWS launched Amazon Bedrock AgentCore Payments in May 2026, built in partnership with Coinbase and Stripe. Connect a wallet, set session-level spending limits, and your agent transacts autonomously. T

Join discussion

KMKartik Mehtawriter.mrmehta.in

0

Watching the Black Box

10h ago · 7 min read · The final part of a series on agent harnesses. We started with the model-plus-harness idea, then built subagents, gave them a safe place to work, and wired up tools, memory, and workflows. This last p

Join discussion

NSNeeloppher Syedneeloppher.hashnode.dev

0

Agentsync: Version, Merge, and Audit AI Agent Configurations Like Code

11h ago · 8 min read · Most AI engineering teams now run a stack of agent configs across many repos - model choices, tool allowlists, prompt templates, eval thresholds, safety rules. These configs drift the moment two engin

Join discussion

KMKartik Mehtawriter.mrmehta.in

0

Hands, Memory, and a Job to Do

11h ago · 7 min read · Part four of a series on agent harnesses. The earlier pieces covered the model-plus-harness idea, subagents, and sandboxes. This one is about the three things that turn a capable agent into one that e

Join discussion

KMKartik Mehtawriter.mrmehta.in

0

Letting Agents Run, Safely

20h ago · 8 min read · Part three of a series on agent harnesses. Part one introduced the model-plus-harness idea, and part two split work across subagents. This piece is about the layer where agents stop just talking and s

Join discussion

KMKartik Mehtawriter.mrmehta.in

0

One Agent Is Not Always Enough

20h ago · 7 min read · Part two of a series on agent harnesses. If you have not read part one, it introduces the idea that an agent is a model plus the harness around it. This piece builds on that, so a quick skim first wil

Join discussion

KMKartik Mehtawriter.mrmehta.in

0

Agent = Model + Harness

21h ago · 8 min read · If you have ever called an LLM API, you already know the basic shape of it. You send some text, you get some text back, and the connection closes. That is a model. It is good at producing language, bu

Join discussion

NPNikhil Pareeknikhil-p-blogs.hashnode.dev

0

Tool-calling eval is four problems, not one

3d ago · 6 min read · I want to start with a trace that still bothers me. An agent fails to book a flight. The model called search_flights with departure_date="next Friday". The endpoint expected an ISO date, returned a 40

Join discussion

JVJason Vertreesjvertrees.hashnode.dev

0

Two Quiet Results, One Shared Lesson: Where Capability Gains Are Coming From Now

3d ago · 4 min read · Two pieces of news showed up this week that are easy to miss in isolation but worth reading together. The first is a developer demonstration: an apparent Opus 4.8 model produced a formally verified pr

Join discussion

YAYe Allenvectronodeai.hashnode.dev

0

How Developers Can Organize AI Model Access in 2026

3d ago · 4 min read · AI applications are becoming more workflow-driven. A developer may start with one model and one simple API call. That is enough for a prototype. But once the product grows, the model layer becomes mor

Join discussion

#agents

Search Hashnode

#agents

Trending tags this week

AWS Bedrock AgentCore Payments: What Your Infrastructure Needs Before You Connect

Watching the Black Box

Agentsync: Version, Merge, and Audit AI Agent Configurations Like Code

Hands, Memory, and a Job to Do

Letting Agents Run, Safely

One Agent Is Not Always Enough

Agent = Model + Harness

Tool-calling eval is four problems, not one

Two Quiet Results, One Shared Lesson: Where Capability Gains Are Coming From Now

How Developers Can Organize AI Model Access in 2026