Starting 2026-10-09, Google cuts the free Gemini App's model lineup (personal accounts) from Flash-Lite/Flash/limited Pro down to Flash-Lite only. AI Plus ($7.99/month) loses Pro access but keeps Flash. AI Pro ($19.99/month) and AI Ultra are unaffected, and AI Pro now also gets Deep Think, a feature previously exclusive to Ultra. This isn't a Gemini API or AI Studio pricing change — it's purely a usage-policy tightening on the consumer app.
The easiest way to fail a Product Sense question isn't running out of ideas — it's being unable to explain, with specifics, why you'd build this feature before that one when resources are tight. Today's practice question is real: 'A social app is gaining traction with teens but has limited engineering bandwidth. As the PM, prioritize these potential features: stories, events, profiles, messaging, analytics.' The answer still runs on CIRCLES — clarify the context and constraints, identify the users, surface their real needs, list the options — but this time the Cut-to-Ladder step gets replaced with RICE scoring: Reach (how many users this touches), Impact (how much it changes their experience), Confidence (how sure you are about those estimates), and Effort (engineering cost), multiplied and divided into one number that turns 'this feels more important' into something a reviewer can challenge and reproduce. The case study is Intercom itself — RICE is the framework PM Sean McBride published on Intercom's own blog in January 2018, built specifically because the team's roadmap debates kept getting won by whoever argued loudest, not by whichever idea actually mattered most.
mcpspan is an open-source, self-hosted analytics dashboard for MCP servers. Install: docker compose up -d to run the dashboard, npm install mcpspan to wire up a server. It solves the problem of a deployed MCP server being a black box about who is calling it, how long calls take, and why they fail.
Hiring guides list 'Tell me about an LLM feature that failed' as a staple LLM engineering behavioral question. It's not testing whether you can fix a bug — it's testing whether you can find a root cause hidden behind an average metric, quantify the real improvement, and turn the fix into a team-wide check. Today's story: a RAG internal-knowledge Q&A bot got PDF table numbers wrong. Overall accuracy looked fine at 81%, but a dedicated table-question slice showed only 32% accuracy. We review this week's six other days — ML Fundamentals, Deep Learning, ML System Design, LLM & Agent Engineering, Coding, and Paper Reading — all seven days delivered with no gaps.
Arena Agent leaderboard, published 2026-10-02: Claude Fable 5.1 (Max) holds #1 at 14.31%, Claude Opus 5.5 (High) stays #2 at 13.82%, and Claude Sonnet 5.5 (Max) — launched only on 09-29 — debuts straight into #3 at 12.52%. GPT-6 Astra (Max) actually ticked up to 12.27% but still dropped to #4, simply overtaken. Arena's official X account confirmed the debut, noting Sonnet 5.5 jumped 8.1 points over its predecessor Sonnet 5 (High), now ranked #13. But the confidence intervals for all four models overlap heavily — a single snapshot can't settle who's actually ahead.
Parakeet Health raised a $10M Series A led by Canvas Ventures, bringing total funding to $13M. The signal: healthcare's fastest path to agent adoption isn't diagnosis — it's the rule-bound, revenue-attributable administrative work like scheduling and recall, where a vendor can win a risk-averse buyer with hard financial numbers instead of a promise about clinical judgment.
Kolibri 1 (`Aleph-Alpha/Kolibri-1`, FP8; `Aleph-Alpha/Kolibri-1-BF16` is the full-precision release): open-sourced 2026-10-03, 78.1B total / 3.46B active parameters (MoE, 384 experts with 6 routed plus 1 shared), context window validated up to 1,048,576 tokens (recommended ≤262,144); fully open weights under Apache 2.0, no official API pricing, self-hosted by design; 96.9% on AIME 2025 (vs. 81.9% for the unreleased predecessor Kolibri Origin), 84.3% on GPQA Diamond (EN), 38.1% on τ³-bench Banking (far ahead of the best competitor's 15.5%); trained with the Merlin-Arthur protocol to abstain rather than hallucinate when context doesn't support an answer; trained in Germany, bilingual by design in German and English, aimed at public-sector, industrial, and aerospace deployments under the EU AI Act and GDPR
Google announced Gemini 4 Argon on 2026-09-30 with an introductory API price of $2.00 input / $10.00 output per 1M tokens (cached input $0.10). Once the introductory period ends, the standard price doubles to $4.00/$20.00 (cached $0.20) — a 100% jump. The announcement only says the increase kicks in 'after the introductory period expires,' with no actual date, and Argon is currently limited to trusted cybersecurity partners with no timeline for general API access.
Behavioral interviews don't test whether you have conflict stories — they test whether you're willing to tell one with real stakes, state your position and evidence clearly, and then genuinely execute once a decision is made instead of quietly resisting. Today's framework is STAR (with 60% of the airtime shifted onto Action and Result, not Situation/Task) paired with Amazon's 'disagree and commit' decision principle. The practice question is: tell me about a time you disagreed with your manager and how you handled it. The approach: pick a real disagreement where both sides had a point, state your position and the evidence behind it, show the turning point where you decided to commit, describe what you actually did to execute, and close with a quantified result plus what you learned. The case study is Jeff Bezos demonstrating disagree and commit himself in his 2016 shareholder letter: he had doubts about an Amazon Studios original's commercial terms, but after stating his full opinion he wrote back immediately, 'I disagree and commit and hope it becomes the most watched thing we've ever made,' letting the team run with their own judgment. The post closes with a recap table of this week's six topics from Product Sense through Technical PM, and a preview of next week.
shipstores is an MCP server that lets an agent like Claude operate App Store Connect and Google Play Console directly. Install: claude mcp add shipstores -- uvx shipstores. It solves the problem where the app is built, but publishing still takes about 40 manual steps, half of which have no public API.
Today's Paper Reading rotation covers arXiv:2609.37658, EnterpriseBench: Benchmarking LLM Agents on Enterprise-Level Strategic Reasoning and Decision-Making — a paper that only went up on arXiv on September 29, 2026. It builds a two-layer evaluation: a foundational layer that reorganizes existing enterprise and financial QA datasets (information extraction, numerical calculation, domain knowledge, complex reasoning), and an interactive layer with three brand-new settings — a simulated consulting interview, a classic Beer Game supply-chain simulation, and an Enterprise Digital Twin project-planning simulator. Running nine agent methods (CoT, Self-Refine, Reflexion, Debate, Discussion, AMEM, DC, GEPA, ACE) across four backbones (DeepSeek-V3, GPT-4.1, DeepSeek-V4-Pro, GLM-5.2), the core finding is that the method that wins on static QA isn't reliably the method that wins on interactive decision-making, and the best-performing method keeps changing depending on both the task and the backbone — there's no universal winner. Core concepts covered: this static-vs-interactive evaluation gap, why Self-Refine and Reflexion actually underperform plain CoT in multi-turn consulting cases, what the win reversals between GEPA/DC/AMEM across tasks and backbones imply, and how the paper validates its own LLM-judge through a three-tier process (a small 20-case sanity check, a 500-transcript multi-annotator study, and prompt-robustness testing). The practice question takes an evaluation-design angle: how do you turn 'there's no universal winner' into an actual agent-selection process, and how do you decide whether an LLM-judge's reliability numbers are good enough to ship to production.
Three things in Pydantic AI v2.53.0: (1) security — GHSA-6fqq-452j-qhrp (high): a streamed request through ConcurrencyLimitedModel or limit_model_concurrency could keep its concurrency slot stuck in a 'released but not really released' state when the consumer exited early (stopped iterating, raised, or was cancelled) or fully consumed stream_text() with its default debouncing; repeating this could block every request sharing the limiter; (2) the fix also changes limiter semantics — a model wrapper now raises UserError when it shares a limiter with the agent making the request or an enclosing wrapper, ConcurrencyLimiter.acquire() takes a new slot on every call (even within the same task), and a custom AbstractConcurrencyLimiter must allow release() from another task; (3) a new ToolCallJudge reviews tool calls before they execute, and the internal repair_messages pipeline is now a public API.
Supabase raised a GIC-led $150M round only four months after its $500M Series F in June, and acquired Turso the same day to support agents that create databases at scale. The signal: backend infrastructure customers are shifting fast from human developers to agents that provision their own databases, and that shift is compressing the company's own fundraising cycle.
Clef (27B, post-trained from Qwen3.8-27B) and Clef-flash (9B, post-trained from Qwen3.5-9B): 64K context window, image/video input support, Clef priced at $0.24/1M input tokens (Clef-flash $0.09, no separate output pricing); 98.5% on BFCL case-exact, 94.2% macro-F1 on BANKING77, 97.4% macro-F1 on CLINC150+OOS — all ahead of Typesafe's Jev. Architecturally it replaces token-by-token generation with a prefill-only scoring pass. It's the third 'decision model' to ship in a single week, after Typesafe Jev, OpenAI's Decisions API, and Amazon's Strands Decider 2B
xAI's grok-imagine-image-quality retires on 2026-11-02 (60-day notice given 9/2). After that date, every request is silently redirected to grok-imagine-image-2.0 with quality forced to low, dropping the price from $0.05 to $0.04 per image (↓20%). The catch: grok-imagine-image-2.0 itself doesn't price by quality tier — anyone who migrates proactively and explicitly sets quality: medium gets better output at the exact same price, while anyone who just waits for the redirect gets stuck on the lowest tier.
Technical PM interviews don't test whether you can draw an architecture diagram — they test whether you can break a breaking API change into concrete decisions: customer segmentation, a compatibility layer, a phased deprecation timeline, and a sunset date you're actually willing to enforce. Today's framework is the five-layer API design model (Use Case → Contract → Compatibility → Operability → Developer Experience), paired with an ADR format (Context → Decision → Consequences → Revisit trigger) for writing decisions down. The practice question is: how would you plan a deprecation for a public API with a breaking auth change? The approach: clarify whether the change is security-driven or a refactor, segment customers by call volume, evaluate whether a compatibility layer can absorb part of the breaking change, then roll out in four phases (warning → outreach → soft deadline → shutdown), tracking migrated-traffic share as the leading indicator. The case study is Stripe: since 2011, every account has been pinned to a date-named API version on its first request, and every breaking change since then has been absorbed by internal version-change modules rather than forced onto developers — a pattern Stripe made explicit in September 2024 with monthly non-breaking releases and two breaking major releases a year.
HarnessRouter Community Edition is an Apache-2.0 self-hosted platform that wraps agent harnesses like Codex, Claude Code, and Hermes behind one API using the Unified Harness Protocol (UHP). Install: docker run -d --name harnessrouter -p 127.0.0.1:3000:3000 -v harnessrouter:/data harnessrouter/harnessrouter. It solves the problem of rewriting session, streaming, file, and cancellation logic every time a product integrates another coding agent harness.
Today's Coding rotation goes a different direction from the batching schedulers and tokenizers covered in past weeks: implement a sample_token function that takes logits, temperature, top_k, and top_p. The core concepts are softmax's numerical stability trick (subtracting the max before exponentiating, or a large logit overflows to inf), temperature's edge case (T=0 is division by zero in the formula, and the industry convention is to fall back to greedy decoding instead of raising an exception), the standard application order (temperature reshapes the distribution first, then top-k trims to a fixed count, then top-p trims dynamically by cumulative probability), and the most common top-p bug — the cumulative-probability cutoff has to compare against the running total *before* adding the current token, not after. The practice question comes from a real AI engineering interview question bank, extended with edge cases like top_k exceeding vocabulary size and a zero-denominator renormalization.
Arena Agent leaderboard, published 2026-09-30: Claude Fable 5.1 (Max) 14.55% first, Claude Opus 5.5 (High) 13.78% second, GPT-6 Astra (Max) 12.18% third. Anthropic markets Opus 5.5 as 'performing close to Fable 5.1 at 40% lower cost,' but in this human-voted Agent category it still trails the flagship by about 0.8 points, and third-party measurements put its max-effort token usage at 4x GPT-6 Astra's. This post also documents a methodology breakthrough: switching to Arena's own historical dataset on Hugging Face (via the datasets-server API) to bypass a month-plus structural failure that had blocked rendering on swebench.com and arena.ai
Three things in Agno v3.1.0: (1) a new `agno.os.authz` package gives AgentOS a native role store, scope policy, audit log, and user directory, with pluggable native and `fga` authorization engines; (2) a new `agno.fs`/`DbFileSystem` adds dedicated `/filesystem` routes to AgentOS, but existing `agno_fs` tables must be migrated offline or they raise `SchemaOutdatedError`; (3) Breaking: `MCPConfig`'s bundled default tools and lifecycle tools (`continue_run`/`cancel_run`) switch from automatically included to explicit opt-in.