Newsletter archive
Applied Signals Weekly: 2026-09-06
Aug 31, 2026 to Sep 06, 2026
In this week’s edition
This week’s edition surfaces where agentic systems face the sharpest pressure points: reliability under coordination, evaluation discipline, and the practical mechanics that keep multi-agent behavior stable over time.
- Agent cost management is about more than the model — Every LLM call your application makes costs money, and agentic applications make a lot of LLM calls. Arize AX now ships a Cost Agent that reads traces, ranks spend, and opens a pull request with the fix. The…
- Terminal-Universe: Turning Agent Trajectories into Scalable Terminal… — As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires:…
- Give Your Coding Agents a Memory You Own
- How AI-native companies turn workflows into operating capability — Basis, Clay, and Exa Labs use AI agents to improve onboarding, account management, and developer integrations. See what enterprise leaders can apply.
- How Coinbase Wallet built an agent-first product development lifecycle — By redesigning planning, validation, and risk review around AI agents, Coinbase Wallet dramatically shortened the path from product idea to working software.
- Introducing agentic video understanding with Gemini
- Legibility is Not Interpretability: Comparing Judged and Actual Importance in… — Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats them as such, using LLM judges to diagnose errors, evaluate…
Worth watching
- frameworks + planning: hype or repeatable pattern?
- planning + tool-use: hype or repeatable pattern?
- frameworks + tool-use: hype or repeatable pattern?
Read the full analysis
- Agent planning meets verifiable execution (weekly trend)
- Sep 06, 2026 Phoenix MCP SQL trace querying cuts per-question cost
- Sep 05, 2026 LatentStream memory, Terminal-Bench environment evolution, step attribution limits
- Sep 04, 2026 HarnessEvo control-slot credit, Speculative Macro Commit latency, PlanFence stale-plan checks
- Sep 03, 2026 Epistemic Sybil Resistance and ArcticSwarm coordination results
- Sep 02, 2026 CUDA-Harness kernels, trajectory-judge paired discrimination, GUI-CC rollouts
- Sep 01, 2026 Evidence-Gated MLOps, AutoSciRub rubrics, and Harness-RL interface training
- Aug 31, 2026 ContextPilot, Logos, LoopArena: context, fault tolerance, control evals
Subscribe
Get Applied Signals weekly newsletter in your inbox