How to Handle a Tool Result Too Large for the Context Window: Truncate, Paginate, or Hand Back a Handle
The overflow that kills agents happens at the one boundary the MCP spec never paginated — the tool result. And the reflex fix, truncating to N characters, is the only option that's strictly worse than doing nothing.
5 min
Together AI Raised $800M at an $8.3B Valuation. The Story Is What Agents Did to Inference Pricing.
A neocloud that owns none of the models it serves just booked $1.15B a year. The number that matters isn't the valuation — it's that open-model inference outgrew the labs whose weights it runs.
5 min
Tencent's Hy3 Is an Open 295B Agent Model. The Number That Matters Is 21B.
A 295B Mixture-of-Experts under Apache 2.0, activating 21B per token. For agent builders, the headline size is the least interesting spec on the card.
4 min
Tabstack: Mozilla's Web-Data API for AI Agents Bets on the Permissioned Web
Mozilla shipped a one-call API that turns any URL into structured JSON, cited research, or a finished browser task. The pitch isn't the features — it's that it obeys robots.txt on purpose.
4 min
SWE-Together vs SWE-bench: The Benchmark That Counts How Often You Corrected the Agent
A new multi-turn coding benchmark reconstructs 109 real user sessions and scores agents on a second axis SWE-bench never had: not just whether they finished, but how much you had to steer them there.
5 min
Semantic Caching Quietly Breaks AI Agents — and Accuracy Isn't the Fix
A cache that skips a duplicate chatbot answer is a savings. A cache that skips a duplicate agent step is a wrong action. New 2026 benchmarks show the standard tools score under 40% — and the fix is the opposite of what you'd guess.
4 min
Retry Budgets for LLM Calls: Why Retrying Every 429 Makes the Outage Worse
Wrapping every model call in retry(3) feels responsible. Under a provider brownout it's the fastest way to turn a slowdown into a blackout. The fix is a budget, not more backoff.
4 min
Qdrant's TurboQuant: Binary-Quant Storage at Scalar-Quant Recall
Qdrant 1.18 shipped a Google Research quantizer that rotates your vectors before it compresses them. The rotation is the whole trick — and the reason it works on any embedding model.
4 min
Pydantic AI V2 Quietly Repointed `openai:` at the Responses API — What Actually Breaks
V2's headline is the Harness. The change that will page you is smaller: the bare `openai:` prefix now resolves to a different OpenAI API, and no deprecation warning fires.
4 min
Poolside's Laguna XS 2.1 Puts a 63%-on-SWE-bench Coding Agent on Your Laptop
A 33B mixture-of-experts model that activates only 3B parameters per token now clears 63% on SWE-bench Multilingual — and ships under a Linux Foundation license. The active-parameter count and the license matter more than the score.
5 min
OpenAI Agents SDK Run Error Handlers: Catching Model Refusals and Invalid Structured Output
v0.17.8 added an `invalid_final_output` handler — a third failure layer that catches what the model itself produces at final output, not what your tools or guardrails do.
5 min
Running Open Models in Claude Code: What the Anthropic-Compatible Endpoint Silently Turns Off
GLM-5.2, Kimi, and MiniMax all ship an Anthropic-compatible endpoint, so pointing Claude Code at them is a one-line base-URL swap. The model runs — but 'compatible' is a promise about the wire format, not about the harness features your bill and your speed depend on.
4 min
Milvus Replaced Kafka and Pulsar With a WAL on S3: Why the Write Path Was the Real Bottleneck
The vector-database benchmark wars are all fought on the read path — recall and QPS. Milvus 2.6 spent its headline engineering on the part nobody charts: the durability log, which it moved straight onto object storage.
5 min
When Your Knowledge Base Learns to grep: LlamaIndex's Retrieval Harness
LlamaIndex's new legal-kb reference app hands the agent findFiles, readFile, and grep — not a search() call. The quiet argument is that retrieval was never the model's job to outsource.
5 min
LangGraph Deferred Nodes: Getting Map-Reduce Fan-In Right
The Send API gives you the fan-out. Deferred nodes are how you get a correct fan-in — but only if you understand that defer=True is a queue-drain barrier, not a dependency resolver.
4 min
LangGraph Checkpointer: Postgres vs Redis Backend Comparison
Choosing a checkpointer backend isn't a speed decision. It's a decision about what lifecycle you want your agent's state to have — a permanent ledger you can replay, or a searchable cache built to expire.
4 min
How to Cap an AI Agent's Spend per Run (max_tokens Won't Save You)
The parameter everyone reaches for limits the size of one reply. Agent bills don't blow up on reply size — they blow up on the number of replies. Cap the loop, not the token.
5 min
How to Cancel a Running AI Agent — and Why Closing the Connection Doesn't Stop It
You press stop. Your socket closes. The GPU keeps decoding, the bill keeps climbing, and a half-finished tool call is still out there. Cancellation isn't a button — it's cooperation.
4 min
DeepSeek's DeepSpec Open-Sources the Hard Part of Speculative Decoding: Training the Draft Model
The speedup was never the bottleneck — the well-matched draft model was. DeepSpec ships the whole draft-training pipeline, MIT-licensed, with Qwen3 and Gemma as the default targets.
4 min
Dead Letter Queues for AI Agent Tasks: Why Redrive Isn't Retry
The dead-letter queue is a solved pattern — for messages. An agent task isn't a message, and the two places that assumption breaks are exactly where your reliability and your token bill live.
4 min
Cognee vs Graphiti vs Mem0: How Much Schema Your Agent's Memory Commits at Write Time
The axis that actually separates the open-source memory engines isn't graph vs vector — it's how much structure each one commits when it stores a fact, and that quietly decides which questions your agent can answer later.
5 min
CISA's Agentic AI Security Guidance: Four of the Five Risks Have No Attacker
The first Five Eyes guide for agentic AI names five risk categories. Read them as a builder and something jumps out — only one requires an adversary. The other four are your own architecture failing quietly.
5 min
China Regulated What an AI May Pretend to Be — So Doubao and Qwen Switched Their Companion Agents Off Rather Than Comply
China's companion-AI law regulates the emotional bond, not the model — so Doubao and Qwen switched their companions off rather than comply. If you ship a persistent persona, here's the tool-vs-companion line coming for you.
6 min
Can You Run an AI Agent on the Batch API? Mostly Not — and What to Batch Instead
An agent is a chain of steps that each depend on the last, so a 24-hour batch window can't sit on the critical path. You can't batch the loop — but the token-heavy work around it is exactly what batch was built for.
4 min
Auto-Generated Eval Rubrics: When the Judge Writes Its Own Grading Criteria
Foundry and Vertex now let a model generate the rubric it will grade your agent against. That closes a loop — and the loop has no fixed point outside itself.
5 min
Anthropic Wants Claude on Microsoft's Maia 200 — Which Would Make It the Fourth Chip Running Inference
A reported deal to rent Azure servers full of Microsoft's inference silicon isn't about capacity. It's a tell about which half of an AI lab's compute is actually up for grabs.
5 min
Agentjacking: How a Fake Sentry Error Hijacks Your AI Coding Agent
A public Sentry key is all an attacker needs to plant a command where your coding agent will read it — and run it. The attack doesn't touch the tool or the server. It rides in on the data you trust.
4 min
Agent Memory Poisoning: Why OWASP's ASI06 Is Prompt Injection That Never Resets
Prompt injection dies when the context window clears. Memory poisoning writes the payload into the store the agent trusts — so it fires in every future session, with the attacker long gone.
4 min
A2UI vs MCP Apps: Two Agent-UI Standards That Bet Opposite Ways on Who Owns the Pixels
Both let an agent return interface instead of text. One ships executable HTML in a sandbox; the other ships JSON to your native components. The gap between them is the whole decision.
4 min
When Should an AI Agent Ask for Help? Why the Trigger Has to Live Outside the Model
Whole-task routing picks a model before the work starts. Agents need something harder: to notice, mid-trajectory, that they're now out of their depth — and three 2026 benchmarks say they can't be trusted to notice it themselves.
5 min