标签：#context

Fabiane Nardon shares how TOTVS prepares enterprise data for token-hungry AI agents. She discusses balancing deterministic logic and non-deterministic LLMs across precision, security, and cost. Nardon details using data mesh, low-latency database architectures, semantic ontologies, and dynamic MCP tool selection to optimize context windows and reduce token overhead in transactional systems. By Fabiane Nardon

Cloudflare is introducing WriteGuard, now in private beta, to provide fine-grained security controls for MCP (Model Context Protocol) servers. It aims to make AI agents safer by controlling their access to tools that can modify data or perform actions, rather than simply read information. By Sergio De Simone

Grafana Labs has announced general availability for two tools that let AI coding agents query live observability data during development: the gcx CLI and the Grafana MCP server. Both allow agents to pull metrics, logs, traces, SLOs, and Synthetic Monitoring results from Grafana Cloud or a self-hosted stack By Claudio Masolo

The MCP 2026-07-28 specification removes the initialize handshake and session header, and adds required method and tool-name headers so gateways can route agent traffic without parsing JSON. Reaction split between developers calling it a rediscovery of REST and those arguing the standard itself was always the point. By Steef-Jan Wiggers

Originally published on Loop & Retry — field notes on building LLM agents that survive production. Here's the failure mode that surprises people who've only reasoned about agents statistically. You measure a per-step error rate — say 10% of steps produce something wrong — and you assume errors are independent, so a wrong step is a wrong step and the rest of the run is fine. Then you watch a real trajectory and see something else: step 4 gets a fact slightly wrong, step 5 reasons on top of that wrong fact and commits harder, step 6 takes an action premised on both, and by step 8 the agent is confidently executing a plan that was doomed at step 4. One mistake became five. The errors weren't independent — they were coupled through the context , and coupling is what turns a 10% step-error rate into a run that's wrong far more than 10% of the time. This is the cascade : a single fault amplifying down a single trajectory. It's distinct from the failure I wrote about in distributed retry patterns , where the problem is one bad condition hitting many workers at once — that's a blast radius, a horizontal spread. The cascade is vertical: it spreads through time within one run, because an agent's own past output is its future input. This post is about the vertical kind, why it's structural rather than bad luck, and where you can cut it. Why coupling is the default, not the exception A stateless function that fails just returns an error. An agent that fails does something worse: it writes the failure down where it can read it again. The mechanism is the same one that makes agents work at all — the transcript accumulates, and every step conditions on everything before it. That's a feature for carrying intent forward. It's also the exact channel a mistake travels down. Three ways a single fault propagates through the context: Poisoned premise. The agent derives or retrieves a wrong fact — a misparsed tool result, a hallucinated ID, a stale value — and it lands in the transcript a

Instacart introduced Blueberry, an AI-assisted incident response system that helps on-call engineers investigate production issues faster. It combines AI agents, operational data, and historical incident knowledge to generate grounded root cause hypotheses in Slack. It uses parallel subagents, MCP integrations, and incident history to reduce investigation time while keeping engineers in control. By Leela Kumili

Microsoft released a dedicated AI Gateway tier of Azure API Management in public preview, with a control plane built around models, MCP servers and tools rather than APIs. It fronts Foundry, Bedrock, Vertex AI and OpenAI behind one endpoint, with policy cards instead of XML. Architects welcomed the consolidation while questioning where the governance boundary sits. By Steef-Jan Wiggers

This article presents a defense-in-depth approach for securing Model Context Protocol (MCP) deployments in production. It outlines four architectural control layers: safe execution, management infrastructure, outbound trust, and semantic integrity, arguing that production security requires enforcement beyond the gateway at the earliest trustworthy control points. By Nik Kale

Traditional API gateways assume deterministic services and simple schemas - assumptions agentic AI breaks. Discover why enterprise engineering leaders are adopting AI Gateways as an evolutionary architecture seam. Centralize guardrails, model routing, agent identity, action policy, and semantic audit within a single control plane to prevent costly incidents while keeping core platforms stable. By Joe Price, Branimir Đurek, Pavlos Migkiros, Trevor Dearham

A few weeks ago, I set out to build a small portfolio project: a Streamlit app that could take any tabular dataset, understand something about its structure, and give honest guidance on how to model it. I called it ContextLens . I expected it to be a practical exercise in Python, machine learning, and deployment. What I didn't expect was how closely it would connect with the same questions I work with every day in my PhD research on context-aware intelligent systems. The problem I started with Most introductory machine-learning tutorials follow a familiar sequence: Load a CSV. Choose a model. Train it. Check the accuracy. What often gets skipped is the layer of judgment that should come before any of that: Is this actually a classification problem or a regression problem? Is the target so imbalanced that accuracy becomes misleading? Is that "ID" column secretly leaking the answer into your model? Are there duplicate rows, missing values, high-cardinality categories, or too many features for the number of available observations? Experienced practitioners make these judgments almost automatically. But that reasoning usually remains invisible—it sits in someone's head rather than inside the system, where another person can inspect it. ContextLens is my attempt to make that layer visible. Upload a dataset, and it profiles the data, flags structural risks—missingness, duplicate rows, likely identifier columns, class imbalance, and high-dimensional settings—and adapts its evaluation guidance to what it finds before training a single model. The point is not simply to train a model. The point is to ask whether the modelling process makes sense in the first place. Why I call it "context-aware" rather than "AI-powered" I was deliberate about this distinction, just as I have been throughout my PhD work, and it turned out to be the most important design decision in the whole project. ContextLens does not claim to be intelligent in the way a human expert is. It does not hide its

QCon AI New York 2026 (Dec 15-16) has opened registration at The Westin Jersey City Newport. Six tracks on production AI, chaired by Eder Ignatowicz with Faye Zhang and Wes Reisz. First sessions announced in August, full program by November. By Artenisa Chatziou

"Context bombing" tricks hacking agents into shutting down before they can do harm.

DoorDash details the architecture behind Ask DoorDash, its AI-powered conversational shopping assistant, combining LLMs, specialized AI agents, MCP-based tooling, and an intelligence layer with persistent consumer memory and live backend data. Early results show up to 24% higher checkout conversion, 17% larger baskets, and improved intent accuracy using memory-backed sessions. By Leela Kumili

GitHub has made the redesigned GitHub Copilot CLI terminal interface generally available. It adds a tabbed layout for sessions, gists, issues, and pull requests; an in-session, form-driven setup for MCP servers, skills, and plugins that avoids hand-editing config files; and a cleaner, theme-aware, more accessible UI with screen reader support. By Mark Silvester

Over the past week, two narratives have been colliding everywhere I look. On one side, there's panic. AI is expected to replace marketers, engineers, and entire categories of knowledge work almost overnight. On the other, there are quieter but far more consequential signals: enterprise teams discovering their AI infrastructure is burning through API budgets far faster than expected. This isn't because the underlying models are weak, but because the systems built around them are fundamentally inefficient by design. These aren't separate stories. They're the same failure showing up in different places. A conversation with another developer made that gap visible in real time. He argued that auditing a 150,000-line codebase requires feeding the entire repository into a model in one single, massive pass. It's still a common assumption in mainstream tech: that an LLM works like a giant biological brain that you must fully load with raw text before it can begin to think. But that assumption is already outdated. Modern AI systems don't scale through brute-force context. They scale through structure. And that shift changes everything. Key takeaways Bigger context windows did not solve AI. Treating a frontier model as a monolithic processor that re-reads an entire system on every query is wasteful, dilutes attention, and hides bugs under raw volume. ARC-AGI-3 makes the gap stark: frontier models scored under 1% on interactive reasoning tasks that untrained humans solve at nearly 100%. The gap is architecture, not memory. The teams pulling ahead treat the model as one narrow component inside a larger system: intelligent routing, task decomposition, retrieval, and only the minimum necessary context. The next advantage is not the biggest model or the longest prompt. It is the system designed around the model. Prompting was the first generation; systems architecture is the next. The Myth of the Infinite Context Window When context windows expanded into the hundreds of thousands o

LLM agents burn a ridiculous number of tokens on redundancy: opening the same files again and again, trying a patch, failing, then wandering back through the repo like they’ve never seen it before. A July 2026 paper, ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair , puts real numbers behind that waste. In repository-level repair, agents keep dragging in irrelevant code and logs. ContextSniper tackles that with a context layer built around tiered memory and an intention-aware context gate that filters low-value regions before they ever reach the model. That gate alone cut tokens by 51.5% on one host agent and 38.9% on Claude Code, while submitted-resolution rates stayed basically in the same neighborhood. The gate is the interesting part, because it is not tied to that paper’s exact system. It is a more general idea, and it is starting to show up across agent architectures. At heart, the gate is just a classifier. Given a request, it has to decide what kind of retrieval will answer the question cheapest: symbol lookup, semantic search, graph impact, mutation prep, or something else. That leads to the practical question the paper does not really answer: Do you need another LLM call just to decide what context to retrieve? We tested that directly. Five ways agents get code into context Before you can gate anything, you need a retrieval strategy. Most current systems fall into one of five rough families: Grounded read-only retrieval: parse the code and return exact symbol source by name. Byte-precise, no synthesis. Graph code intelligence: model calls, imports, entities, and dependencies as a graph, then traverse it. Embedding / RAG search: use vector similarity over chunks. Whole-repo packers: compress or dump the repo into the context window. Mutate / execute runtimes: retrieve context, then modify or run code. None of these is magic. Graphs are great for relationships, but they can drift away from source. RAG is useful, but f

The Model Context Protocol team has promoted its Enterprise-Managed Authorisation extension to stable status, adding a centralised way for organisations to control access to MCP servers through their identity provider. The project states the aim is to replace per-server consent prompts with a zero-touch flow in which users sign in once and then access approved servers without further setup. By Matt Saunders

DeepSeek has previewed its V4 model family, led by a 1.6 trillion-parameter flagship, and made a one-million-token context window the default across all its services. The weights are downloadable and self-hostable, putting frontier-scale long context in reach of smaller labs and individuals without per-token payment to a closed provider. Key facts What: DeepSeek previewed two free-to-download V4 models that can read a million tokens at once, no longer as a premium add-on but as the standard setting. When: 2026-06-29 Primary source: read the source A large language model has no persistent memory. Each time it answers, it re-reads everything in front of it — your question, the conversation so far, any documents you pasted — and that pile of text is the context. The context window is the hard ceiling on how much it can hold at once. For years that ceiling was a few thousand words, then tens of thousands. Pushing it to a million has been possible but expensive, usually sold as a special, pricey tier. DeepSeek's move is to make a million the everyday default. The family comes in two sizes. V4-Pro is the big one — 1.6 trillion parameters in total, but only about 49 billion of them switch on for any given word. That design is called a mixture of experts : instead of running the entire brain for every token, the model routes each piece of text to a small relevant subset of specialists, so it stays affordable to run despite its enormous size. V4-Flash is the smaller, cheaper, faster sibling, meant for everyday chat and quick edits, and DeepSeek says it keeps up with Pro on simpler agent tasks. Making a million-token window affordable comes down to how the model handles its KV cache — the running set of notes it stores about every previous word, which grows steadily the longer the conversation gets. At a million tokens those notes become a mountain of memory, and the model normally has to consult every note for every new word it writes. DeepSeek's approach, which they call sp

If you run a RAG system in production, you eventually hit a dilemma that has nothing to do with your model and everything to do with your cache. Cache the answers to save tokens and latency, and one day a source document changes — but your cache keeps cheerfully serving the answer it built from the old document. Nobody gets an error. The number is just quietly wrong. Cache nothing , and every single call re-retrieves the same chunks, re-reads them, and re-pays the full context bill to rebuild an understanding you already built five minutes ago for a nearly identical question. Stale or expensive. Most teams pick "expensive" because at least it's correct, then bolt on a TTL and hope. This post is about why the TTL doesn't save you, and about two specific, mechanical fixes that let you cache RAG context and stay fresh. I maintain an open-source library called Coalent that implements both, so I'll use it for the runnable examples — but the two ideas are portable and worth stealing even if you never pip install anything. Failure mode 1: the stale RAG cache (and why a TTL won't save you) Here's the standard "answer cache" sitting in front of retrieval: answer = cache . get ( query ) if answer is None : chunks = retriever . retrieve ( query ) answer = llm . synthesize ( query , chunks ) cache . set ( query , answer , ttl = 3600 ) return answer This works until billing.md changes. The refund window goes from 30 days to 14. Your cache has an answer keyed on "what is our refund policy?" that says 30, and it will keep saying 30 for up to an hour — or forever, if the same question keeps refreshing a TTL that never expires under load. The reason this is hard is that the cache key (the query) has no relationship to the thing that changed (the source). You cached an answer; you threw away the fact that this particular answer was derived from billing.md . So when billing.md changes, you have no way to find the answers that depended on it. The TTL is a confession that you can't answ

X has launched a hosted MCP server, making it easier for developers to connect AI applications with the company’s API.