Multi-Agent Systems.Supervisors, handoffs, swarms — and when each one breaks.

August 2026 model routing: put Grok 4.6, Qwen3.8-Max, and DeepSeek V4-Flash into cost-per-completed-task lanes

Between July 31 and August 12 we got DeepSeek V4-Flash public beta, Qwen3.8-Max on Alibaba Cloud, and Grok 4.6 for long-running agents. List prices look similar at the top. Behavior does not. Here is how I redraw planner vs worker lanes around cost per completed task, what I refuse to claim yet about open weights, and the checklist I use before a new model ID touches production routing.

Aug 13, 202616 min

Cursor's agent swarm economics: why frontier planners and cheap workers beat solo GPT bills

Cursor's July 2026 swarm write-up rebuilt SQLite in Rust from the docs and measured planner vs worker spend. Frontier-only GPT-5.5 hit about $10.5k; Opus 4.8 planning with Composer 2.5 workers landed near $1.3k at similar quality. Here is how I translate that into routing rules for production graphs.

Jul 29, 202615 min

Graph engineering with Claude Code: the 14-step roadmap I use when linear agents stall

A straight-line agent is a degenerate graph. Claude Code dynamic workflows move orchestration into JavaScript so subagents fan out, verify, and converge without stuffing every intermediate result into one context window. Here is the 14-step roadmap I map onto production work, with topology diagrams, contracts, and the patterns I already ship.

Jul 22, 202622 min

The maker is not the verifier: how I build self-improving agent loops without pretending models self-learn

Most teams prompt harder, get a better answer, and start over tomorrow. That is not compounding. Self-learning updates model weights from experience; no public model including Fable 5 does that today. Self-improving means the system gets better: run, log, distill, repeat. The golden rule is maker ≠ verifier. Here is the four-layer architecture and loop patterns I ship.

Jul 9, 202614 min

How to actually use Fable 5: the four-layer architecture behind Mythos-tier results

Fable 5 is back globally, but most teams use it like a bigger Sonnet: prompt harder, better answer, start over tomorrow. Mythos-tier models need Mythos-tier systems: primitives, orchestration, memory, and self-improvement. The golden rule is maker ≠ verifier. Here is the architecture I draw on every engagement after the July 7 billing cliff.

Jul 7, 202614 min

Codex Record and Replay turns one demo into a Computer Use skill: how I inspect generated skills before trusting them unattended

Codex app 26.616 adds Record and Replay on macOS: perform a workflow once, Codex packages it into a skill you replay with different inputs. Thread handoff and automation run history ship alongside. Computer Use must be enabled. Here is the review checklist I run before any recorded skill runs unattended.

Jul 3, 202613 min

Agentic RAG vs vanilla RAG: why a Sufficient Context Agent beats retrieve-then-pray

Google Research shipped Agentic RAG on Gemini Enterprise with a Sufficient Context Agent that refuses to answer when retrieval is incomplete. On factuality benchmarks they report up to 34% higher accuracy versus standard RAG. Here is when one-shot RAG is still enough, when you need iterative retrieval, and how I wire the pattern without blowing latency budgets.

Jun 6, 202614 min

Inside Recruiting Atelier: a runnable reference for the primitives of an agentic system

A working open studio that vets duplicates, plans the run, screens, scores, shortlists, and notifies. The whole pipeline lives in roughly ninety lines of supervisor code and a tool registry you can read in one sitting. Here is what is inside, why every piece is there, and what you can copy into your own stack.

May 24, 202614 min

AI agent vs agentic AI: what the distinction actually means when you ship one

Vendors blur the line because "agentic" sells. The two terms describe different architectures, with different cost shapes, different observability needs, and different scoping conversations. Here is the framing I use with clients and the three-question test for which one your project actually needs.

May 22, 202612 min

Why I am replacing supervisor patterns with handoffs

Supervisors looked clean on paper and shipped slow in production. Handoffs read messier in the code but recover better when an agent loses the plot. Two real systems and where supervisors still earn their keep.

Apr 26, 20268 min

Three patterns I broke in 2025, and what I do instead now

Self-correction loops without budgets, single-agent solutions to multi-domain problems, and using JSON mode to force structure I should have built into the schema. An honest review.

Mar 14, 20268 min

Haiku 4.5 made our router 5x cheaper. The trade-off matters

Replacing Sonnet with Haiku in the dispatcher role cut our orchestration cost dramatically. It also cost us in two specific places I did not predict.

Feb 22, 20267 min

Read the post

4 carousel notes

Visual breakdowns on Multi-Agent Systems

Architecture

Graph engineering with Claude.

Your agent is already a graph. Stop drawing it as a line. 14 steps, four phases.

Architecture

How to actually use Fable 5.

Mythos-tier model. Sonnet-tier habits. Four layers, one golden rule: maker ≠ verifier.

Production

Agentic AI content quality: 5 agents, one pipeline.

Separate eval from rewrite, route models per agent, guard inputs and outputs. Run it on every page before publish.

Multi-Agent

Sequential or parallel? Draw the flow.

Most multi-agent systems pick the wrong execution flow. One question tells you which to use.

See the full Multi-Agent Systems update feed

41 ship-news updates

Latest in Multi-Agent Systems

Research

Anthropic reports Claude produced the first end-to-end Lean formalization of Fermat’s Last Theorem

September 4, 2026 · via Anthropic

Open Source

Z.ai open-sources GLM-5.3-Flash, a 320B-A18B multimodal worker model for coding and agent loops

August 26, 2026 · via Z.ai

Open Source

Alibaba Qwen opens Qwen3.8-Flash-Next weights as a Qwen4-architecture preview for efficient multimodal agents

August 24, 2026 · via Qwen

Open Source

NVIDIA Megatron Core 0.19.0 adds DeepSeek V4 HybridModel paths, MLA, DSA, and MXFP8 training support

August 19, 2026 · via NVIDIA

Research

Anthropic reports Claude designed protein binders against 14 of 15 targets with 22 to 35% hit rates

August 18, 2026 · via Anthropic

Open Source

Alibaba releases Qwen3.8-27B and open-weights Qwen3.8-2.4T-A95B for multimodal, long-horizon agent builds

August 17, 2026 · via Alibaba Cloud

Tools

Google launches Gemini 3.7 Flash for coding and agents with 1M context and introductory production pricing

August 13, 2026 · via Google

Tools

Grok 4.6 ships for long-running agents: $2/$6, live in Cursor and Grok Build, matches Sol on AA Intelligence Index

August 12, 2026 · via xAI

Architecture

Claude Code Week 32: cross-session messaging on macOS/Linux, plus Focus view and sandbox credential masking

August 7, 2026 · via Claude Code

Enterprise solutions

How Multi-Agent Systems ships in our engagements

The pages below are the buyer-focused, conversion-grade versions of this topic — deliverables, methodology, ROI, security considerations, and CTAs to scope a real engagement.

Explore the Agentic AI Consulting solution

Agentic AI Consulting

Designed, built, and handed off — production agentic systems for enterprise teams.

Explore the AI Systems Engineering Training solution

AI Systems Engineering Training

Eight-day corporate training programs that take dev teams from AI-assisted coding to production agentic systems.

Explore the Enterprise AI Architecture solution

Enterprise AI Architecture

Reference architectures for organisations standing up an AI platform — not one agent, but the foundation for many.

Explore the AI Observability solution

AI Observability

Tracing, eval, cache-hit telemetry, and cost attribution for production agents.