OpenAI's Node SDK sent three requests to a failing mock server because the agent harness above it leaves maxRetries at the SDK default of two. The one-attempt rule held only after a guard was locked onto globalThis.fetch, where a startup call had silently replaced the first one.
Reality
- Evidence55
- Adoption
- Insufficient
- Hype gap0
- Incentives
- Insufficient
- Confidence50
The share was around 20% four months ago, and the same newsletter describes engineers building standup bots and PR monitors to keep up. PostHog did not publish merge or rework rates for the agent-opened PRs.
Publishers:newsletter.posthog.com
Reality
- Evidence34
- Adoption46
- Hype gap+31
- Incentives72
- Confidence56
A seven-part video walkthrough is packaging the Flask creator's Pi workflow for a general audience. The harness itself leaves isolation to the operator, and Earendil's own documentation says so plainly.
Reality
- Evidence66
- Adoption18
- Hype gap+22
- Incentives66
- Confidence55
A retrospective on oioannou.com describes an agent that began with read-only ClickHouse access in January 2026, grew into Slack, Linear, PostHog and Grafana through thin CLI wrappers, and now consumes billions of tokens a month.
Publishers:oioannou.com
Reality
- Evidence40
- Adoption32
- Hype gap+14
- Incentives45
- Confidence46
Most Bayesian modes ship a flat prior stopped on a posterior-probability threshold, a pairing Spotify's engineers say reproduces the false positive rate of frequentist peeking while sounding easier to interpret.
Publishers:engineering.atspotify.com
Reality
- Evidence48
- Adoption42
- Hype gap+12
- Incentives62
- Confidence54
PostHog put 344 visitors against exactly 344 pageviews on one country row, which is arithmetic no crowd of humans commits, and whatever produced it ran enough JavaScript to sail past a server-side filter.
Reality
- Evidence42
- Adoption18
- Hype gap+5
- Incentives38
- Confidence47
The public software-factory writeups agree about the pipeline and disagree about who merges. That disagreement is the staffing question, because agents made code cheap to generate and left the cost of reading it alone.
Reality
- Evidence42
- Adoption71
- Hype gap+18
- Incentives72
- Confidence47
Anthropic has cut 80% of Claude Code's system prompt. PostHog's audit of its own agent config file suggests the maintenance job now runs the other way, toward subtraction. A stale line is the cautionary case.
Publishers:newsletter.posthog.com
Reality
- Evidence42
- Adoption38
- Hype gap+18
- Incentives66
- Confidence45
PostHog cannibalized its agentic Code product: self-driving shipped inside Web, the leftover shell became Desktop, and the company says Desktop still has no product-market fit.
Publishers:newsletter.posthog.com
Reality
- Evidence42
- Adoption26
- Hype gap−18
- Incentives74
- Confidence56
A batched track call with no event name is accepted and then dropped before any destination sees it, according to an open source linter's Segment rule pack. The response code will not tell you.
Reality
- Evidence38
- Adoption
- Insufficient
- Hype gap+18
- Incentives74
- Confidence45
A six month backfill can land entirely on today with no error anywhere in the response. The docs ask for ISO 8601, and a number is accepted and then overwritten at ingestion.
Reality
- Evidence48
- Adoption
- Insufficient
- Hype gap+9
- Incentives70
- Confidence46
PostHog asked Claude, Cursor and its own assistant the same revenue question and got three answers. Its remedy was a governed catalog of definitions stored as ordinary SQL tables.
Publishers:posthog.com
Reality
- Evidence34
- Adoption21
- Hype gap+22
- Incentives78
- Confidence42
PostHog says one product's LLM cost doubled from $5k to $10k in a day and it was not a regression. Without per-workflow tracking, growth and a defect look identical on the invoice.
Publishers:newsletter.posthog.com
Reality
- Evidence46
- Adoption34
- Hype gap+16
- Incentives70
- Confidence50
A solo operator with no engineering background shipped a paying eSIM store, then published six failures. Not one of them was a coding problem.
Reality
- Evidence34
- Adoption22
- Hype gap+12
- Incentives52
- Confidence38