Today's Coding rotation works through a real xAI interview question — implement dynamic batching for token decoding, refilling finished slots in a fixed-capacity batch B while correctly handling three stop conditions (stop_token, stop_sequence, max_tokens) and keeping the slot_id-to-request_id mapping correct. Core concepts cover how continuous batching trades off GPU utilization against latency, using NumPy broadcasting and boolean masks instead of explicit loops, padding and attention masks for variable-length inputs, and why a production batch inference API should scale on queue depth rather than raw GPU utilization. Bonus: a meta-point on interview design — 2026 ML coding interviews increasingly skip rote algorithm recall in favor of realistic production scenarios like today's, testing engineering judgment instead.
Clay closed a $115M Series D led by Wellington Management, an asset manager with roughly $1.4 trillion under management, pushing its valuation from $3.1B last August to $7.1B. This round signals that Wall Street asset managers — not just traditional VCs — now treat AI-agent-driven GTM automation as a predictable, scalable enterprise software category worth betting on.
Euno closed a $23M Series A led by N47, with co-founders of security startups Wiz, Cyera, and Eon joining as angel investors, bringing total funding to $29M. The round signals that the next infrastructure battleground for enterprise AI agents isn't memory capacity — it's a context layer that keeps learning and enforces governance rules in real time.
DeepSeek-V4.1-Flash (`deepseek-flash`) is a 552B MoE with 8B prefill and 16B decode active parameters, a 1M-token context window, and 384K maximum output. It is MIT-licensed, priced at $0.30 input and $1.20 output per million peak-hour tokens, and brings CED, CSA2, and FP4 KV-cache compression to agent workloads.
Nex-N2.5-mini (`nex-agi/Nex-N2.5-mini`) is a 35B MoE with about 3B active parameters, a 262,144-token context window, Apache-2.0 licensing, and a free OpenRouter tier. Nex reports large gains over N2-mini on DeepSWE and Terminal-Bench, with visual-feedback self-correction as its central design goal.
India's National Payments Corporation (NPCI) is building a Unified Agent Protocol that would let AI agents make payments on a user's behalf over UPI, possibly unveiled at the Global Fintech Fest in Mumbai (Sept 8-11); Bengaluru startup Gnani AI used the same event to announce its sovereign AI stack, Gnani Artha, expanding into banking, insurance, and financial services (BFSI); around the same time, Visa, Mastercard, and Ant International announced a cross-network AI agent identity framework called KYA — signaling that 'who gets to verify an AI agent's identity' is becoming a new battleground in global payments.
On September 10, NVIDIA announced it will work with 8 Australian cloud and data center partners to build out AI compute capacity to 2GW by 2027 — more than doubling existing capacity; around the same time, New Zealand's Labour Party released an AI Action Plan explicitly modeled on the Australian government's AI governance framework from July 15, including a proposed Office of AI; and Adelaide startup Metacognition AI raised a AU$10 million seed round to build a robotics operating system. Infrastructure, governance, and startup capital are all moving at once, with Australia and New Zealand's policies explicitly aligned.
GreyNoise and Blackpoint Cyber independently tracked the same campaign: since August 31, a suspected Russian-speaking actor chained CVE-2026-81578 (auth bypass) and CVE-2026-82078 (unsafe dynamic class loading RCE) in PaperCut NG/MF, built target lists via Netlas.io scanning, then unleashed hundreds of AI agents powered by OpenAI Codex and a DeepSeek model — backed by the Hindsight persistent-memory service and the AionUi multi-agent workspace — to automate Mimikatz, SharpHound, Certipy, Rubeus, and Impacket. The campaign has compromised 440 servers across 395 organizations in 48 countries; one target went from initial access to full domain administrator in seven minutes. Defense: upgrade immediately to PaperCut's Emergency Patch Release 2, and check whether NTDS.DIT has already been exfiltrated via DCSync.
skills is Serverpod's open-source CLI: package authors ship a skills/ directory with their Dart/Flutter package, and users run skills get to auto-install every dependency's Agent Skill into Claude Code, Cursor, Codex, and more. Install: dart pub global activate skills. It addresses the problem of AI assistants not knowing how to use a third-party package without manually pasted docs or hand-written rule files.
A pre-registered, 345,600-request controlled study finds an accountability layer that reads agents' own filed reports mostly relays their conclusions instead of independently checking them — deleting one 'stated conclusion' clause recovers 41.2 points of attribution accuracy; when authority state lives outside an agent's visible workspace, giving the planner more evidence doesn't fix unsafe actions, but a check applied at the moment of execution blocks all 6 unsafe intents; and a real, ungoverned population of thousands of AI agents in the wild reproduced its entire collective behavior through nothing but copying whatever was most visible, which means whoever writes first sets the convention
Taiwan's Ministry of Digital Affairs proposed a six-layer AI agent governance framework that explicitly names accountability, but today's arxiv paper shows most audit layers read an agent's self-written report and score only 4.1% attribution accuracy when no node volunteers the real cause — worse than random guessing; Google's GTIG disclosed that a financially motivated actor stole thousands of credentials in under six hours using one prompt and a markdown playbook, while a leaked C2 server was found actively managing over 23,800 stolen credentials; DeepSeek's coding-agent harness and Langflow each disclosed CVSS 9.4/9.8 critical flaws the same week Tencent open-sourced a scanner covering 1,600+ CVEs; Taiwan Mobile unveiled enterprise agent platform MyAgent, claiming a 30% end-to-end workflow efficiency gain
obra/superpowers hardens a full development methodology into a skill installable across 8+ harnesses; affaan-m/ECC is a performance-optimization system with 68 agents + 286 skills for agent harnesses; cathrynlavery/diagram-design gained 2,286 stars in a single day, swapping Mermaid for 39 editorial diagram types; Tencent's teamai-cli lets a team distribute skill/rule/MCP config centrally; Pydantic AI v2.42.0 adds a GitHub Copilot provider
This round of LLM & Agent Engineering focuses on the architecture decisions interviewers dig into most in 2026: RAG and agents aren't an either/or choice but a division of labor — RAG handles cited, grounded policy Q&A, while an agent only steps in when the task needs multi-step, cross-system actions. Guardrails split into offline evaluation (catching regressions before release) and online interception (blocking unsafe outputs in real time), governed by one core principle: the model proposes, and a deterministic system authorizes and executes. On evaluation, beyond standard LLM-as-a-Judge scoring, agents also need trajectory-based evaluation that checks each intermediate decision, not just the final answer. Today's practice question is a PracHub-compiled 'design an enterprise support agent' system design prompt, drilling how to separate the RAG path from the agent path and make the authorization layer the centerpiece of your answer.
Mastra @mastra/core@1.65.0 highlights: (1) a new advanced trace query contract implemented across ClickHouse, DuckDB, and Postgres, with bounded time ranges, recursive predicates, and cursor pagination; (2) tenant-scoped batch deletion (up to 1,000 traces per request) that cascades to spans/scores/feedback/metrics/logs; (3) breaking: `@mastra/factory`'s `defineBoard()` becomes a typed phase contract, the global rules object is removed, and two `@mastra/playground-ui` components got renamed slots/props.
Pydantic AI v2.42.0 highlights: (1) a new `GitHubCopilotProvider` lets Agents use GitHub Copilot's OpenAI-compatible API directly as a model backend; (2) `DeferredToolResults.approvals` now rejects invalid values outright — a compatibility change; (3) fixes for Bedrock Converse sampling settings, `$ref` resolution in code-mode function schemas, and lost Anthropic error-recovery state across normalized history.
Cymphony closed a $25M Series A co-led by Sequoia and SMBC Fin Atlas Beyond Fund, bringing total funding — including Sequoia's earlier seed — to $30M at a post-money valuation above $100M. This is Sequoia betting twice on the same team in a market — AI agent identity and data security — that hasn't yet proven itself as a standalone category. The bet isn't on whether the need exists, but on whether it becomes the next must-buy line item in enterprise security budgets.
Harvey closed a $550M round co-led by new investors Diffusion and Lightspeed, pushing its valuation from $11B in March to $15.5B — nearly doubling in nine months. Half the money buys confidence for its own fine-tuned model, half buys agent-security capability via the Guardrails AI acquisition: Harvey is shifting from a law-firm AI assistant into a vertical AI company that trains its own models and manages its own agent risk.
The easiest way to fumble an AI Product Design question is to turn "should we use AI" into a matter of belief, without naming which specific class of task can be automated and which must keep a human in the loop. Today we use a risk-by-confidence matrix to sort tasks into auto-executable, needs-review, and human-required zones, then use progressive delegation to design the cadence at which users actually earn trust in AI, practicing a design prompt about an ops team that won't let AI autonomously run multi-step tasks. The case study is Gusto's AI product Cofounder, whose team publicly explained in September 2026 that AI-moderated interviews are reserved for narrowly scoped, low-risk evaluative research, while depth work always goes to a human researcher.
Google GTIG's Q3 2026 AI Threat Tracker, published in September, describes an incident Mandiant investigated in Q2 2026: after breaching an organization's cloud environment, a financially motivated actor used nothing more than an AI coding chatbot, a prompt, and a set of pre-written markdown instructions as an 'operational playbook' to autonomously scan, exploit, harvest credentials, troubleshoot in real time, and rotate IPs — compromising thousands of third-party credentials in under six hours. The same report separately describes an exposed command-and-control server running Recon, an automated reconnaissance and credential-management framework built on the open-source OpenClaw agent framework, complete with AGENTS.md and KNOWLEDGE.md configuration files; once discovered, the exposed directory had already turned into a live production dashboard managing over 23,800 stolen cloud and AI service API keys. The Hacker News, BleepingComputer, Help Net Security, and Cyber Magazine have all corroborated the report. Defense: audit cloud environments for anomalously fast automated API call patterns, restrict how much credential access any single coding agent session can reach, and compress your response window from days to minutes.
ToolHive is Stacklok's open-source MCP server runtime management platform. Its CLI (thv) or Kubernetes Operator runs every MCP server in an isolated container. Install: brew install stacklok/tap/thv. It addresses the problem of MCP servers running directly on your machine with your machine's own credentials and network access.