🔍 A DeepSeek Harness Plugin That Lets AI Explain the Agent's Own Trace Less than two weeks after DeepSeek Harness entered developer preview, its plugin ecosystem is already taking shape. Zhihu contributor 刘琦 built DSH Trace Insight, a focused plugin for one of the most important but overlooked parts of Agent engineering: understanding what an Agent actually did. 1️⃣ DeepSeek Harness exposes the process Many Agent harnesses behave like black boxes. Users provide a task, wait, and eventually receive an answer. DeepSeek Harness is different. Its trace records tool calls, execution steps, failures, retries, and other intermediate activity. This makes the Agent more transparent, but the raw trace is stored as a large JSONL file. Even with filtering, it is difficult for a human to read and reconstruct the full process. The author's idea was straightforward: If the trace is too complicated for humans, let another AI interpret it. 2️⃣ Turn raw traces into readable analysis DSH Trace Insight adds a side panel that asks an AI model to explain the running trace. It can summarize: 🔹 What the Agent is doing 🔹 Which methods and tools it used 🔹 Where errors or retries occurred 🔹 Whether any risky actions appeared 🔹 What lessons can be extracted from the run Instead of waiting beside an opaque progress indicator, users can inspect how the task is progressing, whether the approach is working, and how risky the current behavior looks. The goal is not to add another capability to the executing Agent. It is to add an interpretability layer around the Agent's behavior. 3️⃣ Use two models for cross-checking When a suspicious step appears, the plugin can send the same trace to two different AI models and compare their analyses. This is useful because trace interpretation is still a model-generated judgment. A second model can expose disagreements, missed risks, or different readings of the same tool call. The plugin can also organize detected issues into a compact list for manual review. That creates a useful three-layer workflow: Agent execution → AI trace analysis → human review It is a lightweight approach to Agent observability without requiring users to inspect thousands of raw log lines. 4️⃣ Installation is intentionally simple The plugin is open source under the MIT license: Users can ask their Agent to install it directly with: Please install this DSH plugin: The current version is designed for the native DeepSeek Harness Web UI. Using it inside third-party desktop wrappers may require additional development, since those clients may package or modify the original Web UI differently. 5️⃣ DeepSeek Harness can become a model worker behind Codex The author also suggests an interesting setup for people who do not use DeepSeek Harness as their primary Agent interface. Open the native DSH Web UI inside Codex's browser. Codex remains the main harness, while it operates DeepSeek Harness and the models connected to it. This creates a layered workflow: 🔹 Codex handles planning and orchestration. 🔹 Lower-cost non-GPT models inside DSH perform lightweight tasks or code inspection. 🔹 DSH Trace Insight exposes how those models executed the work. 🔹 Codex can discuss the results with DSH across multiple rounds, then send the final conclusion to another strong model for an additional review. Compared with assigning every subtask to an expensive model, this setup can reduce cost. Compared with calling another CLI tool blindly, it provides much better visibility into execution. ✅ The real value is observability DSH Trace Insight does one thing: it translates an Agent's raw execution history into something humans can understand. That simplicity is its strength. As Agents begin running longer tasks with more tools and greater autonomy, the important question is no longer just whether they produced the correct answer. We also need to know how they reached it, what failed along the way, and whether they crossed any risky boundaries. 🔗 Full Reading: #DeepSeek# #DeepSeekHarness# #AIAgents# #AgentObservability# #OpenSourceAI# #AIEngineering#

Protect sensitive data without giving up voice agent observability. LiveKit PII Redaction automatically removes personal information from transcripts and recordings before it is stored. It is included with LiveKit Agent Observability at no additional cost. Read more:

🧠 4. AGENT FLIGHT RECORDER Give Hermes accountability. Record the important trail: • decisions • tool calls • file changes • agent handoffs • failures • recovery attempts Then you should be able to ask: -What changed?” -Which agent changed it?” -Why did you do that?” -Can I roll it back?” Why: Agent observability becomes more important as autonomy increases.

Day one at #CiscoLiveAPJC# Melbourne, and the NVIDIA AI Labs room was packed. 🛠️ Developers got hands-on with a multi-agent healthcare assistant powered by NVIDIA NIM and Nemotron open models, with Splunk Agent Observability and Cisco AI Defense in action. We're just getting started. Join us at the next NVIDIA AI Labs sessions: 📅 Nov 11 | 11:00 AM–12:15 PM 📅 Nov 12 | 10:00–11:15 AM See you there!

Want AI you can control and trust? 🤖🔒 Join Cisco and NVIDIA at Cisco Live Melbourne for a hands-on lab exploring open-weight AI, agent observability and real-time guardrails. 📅 Mon 9 Nov, 3:30–4:45pm 📅 Wed 11 Nov, 11:00am–12:15pm 📅 Thu 12 Nov, 10:00–11:15am Seats are limited. Sign up to secure your spot 👉 #CiscoLiveAPJC#

Want AI you can control and trust? 🤖🔒 Join Cisco and NVIDIA at Cisco Live Melbourne for a hands-on lab exploring open-weight AI, agent observability and real-time guardrails. 📅 Mon 9 Nov, 1:30–2:45pm 📅 Tue 10 Nov, 1:30–2:45pm 📅 Wed 11 Nov, 11:00am–12:15pm Seats are limited. Sign up to secure your spot 👉 #CiscoLiveAPJC#

DYNATRACE $DT price-target raised to $74 (from $65) at UBS, while maintaining a Buy rating: "Demand for AI/agent observability is inflecting, boosted by recent AI governance/safety concerns, which could be a material catalyst for DT/DDOG shares and with this initial deep-dive we focus on DT's Arize acquisition but we also offer insights relevant for DDOG. Net, we conclude that both DT and DDOG will likely be key beneficiaries of rising AI observability spend which our checks suggested could reach 20-25% of total observability spend over the next few years, enough to drive at least a few points of growth for both DT/DDOG in each of the next few years. We spoke with 4 F500 customers of Arize and overall we came away more positive on both the AI observability opportunity and the strategic rationale for the Arize acquisition with all 4 existing Arize customers expecting an aggressive spend ramp over the next several years (3 of 4 were customers of both DDOG+DT). Our work suggested that Arize + AI observability will be key to DT’s ability to drive high-teens c/c ARR growth over the next few years (UBSe 19%/18%/19% in FY27-29)."

Moving AI agents from prototype to production faster than ever? Don't let rapid iteration hide critical runtime behavior. Tune in to What's New Wednesdays: Vibe-code, trace, and deploy your agents to explore: • Production agent observability workflows in W&B Weave • Evaluating and self-improving agent loops at scale • Real-world takeaways from CoreWeave Hacks Register here:

❄️ The October Snow Report is LIVE ❄️ CoWork automations, Elastic Channels, and a hands-on lab to build and deploy an app with CoCo. 🚀 What's new CoWork Automations are GA Schedule recurring reports in plain language. CoWork runs the question on fresh data and emails you the summary, key metrics, and a link to the full report. Snowpipe Streaming Elastic Channels are GA A pipe gets a server-scaled ingestion path for many producers streaming to Snowflake tables or Iceberg tables. Choose Named Channels for ordered, exactly-once ingestion. 🗓️What's ahead Oct 15: Snowflake Connect – bring enterprise knowledge together to power trusted AI Oct 20: Snowflake AI Pulse – newest Cortex AI capabilities live Oct 21: Level up dbt workflows with CoCo – live demo Oct 22: Agent Observability from Observe by Snowflake – cost, quality and behavior in production Oct 27: Hands-on lab – go from prompt to deployed app with CoCo and Snowflake App Runtime Nov 3–6: Expedition 2026 – the global virtual event. Registration is open now. ➡️ Watch the full report and get everything in one place.

The hyperscalers didn’t just build businesses renting out CPU compute. They built extremely valuable products around data, networking, security, storage, etc. We’re now building around AI accelerators, but the playbook of building value add software on top is the same. Turns out GPUs are really good for running AI models. That is why inference engines, which take a trained model and compute and produce intelligent tokens that can do real work, have become the first piece of this software stack. But, there is so much more to build than just this! Training helps you turn compute into better models that produce more valuable tokens. Routing helps you pick the right model to generate those tokens at the right cost and quality. Security monitoring helps you check what’s going into and coming out of those models. Then there’s agent observability, context management, sandboxing, etc. All of these things will be part of the new AI stack and the opportunity is much bigger than just serving a model. This definitely isn’t a winner-take-all market, whether we’re talking about open models vs. the frontier or the players within each category. Customers want choice, flexibility, and access to the fundamental building blocks to create their own systems. Constrained GPU supply will actually act like a regularizer and draw this fight out longer. Customers are looking for both compute capacity AND value add on top of it. When someone doesn't have capacity, you go somewhere else. That means more players get exposure to customers and the opportunity to address value add. Getting a customer because you have available GPUs is different from keeping them because your software is better. In the limit, the value add on top of the GPU will win out. The companies that do the best job building that software AND verticalize the fastest to own everything from chip to token will take the lion’s share. It’s important to be building for that now, even when the immediate customer need is just more compute.