Andreessen Horowitz and individual investors put $42 million into a one-year, unaccredited San Francisco program whose first class of about 50 pays nothing. The paying version, at $60,000 to $90,000 a year, needs regulatory approval.
Perspective Coverage
5 publishers
- Builder
- Builder 29%
- Operator
- Operator 32%
- Investor
- Investor 39%
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+35
- Incentives75
- Confidence60
buildOne report1 publisher Context rot piece maps two of five failure modes, position bias and attention dilution, before breaking off mid-sentence
A dev.to piece on harness engineering splits agent degradation into five separable failure modes. The two it actually describes both turn on where a token sits in the assembled prompt, and a bigger window leaves both in place.
Reality
- Evidence24
- Adoption
- Not scored
- Hype gap+30
- Incentives68
- Confidence55
buildOne report1 publisher Agents stall on tool surfaces, not models: tool design as an engineering discipline
A dev.to series entry on the harness tool layer argues fifty bespoke tools are worse than read_file and bash. The usable test is whether one tool already expresses another.
Reality
- Evidence28
- Adoption
- Not scored
- Hype gap+24
- Incentives68
- Confidence34
buildOne report1 publisher Your agent's blast radius is decided by the filesystem, not the prompt
Part 6 of dev.to's Harness Engineering series puts the runtime where tool calls execute at the center of agent safety. Its list of things a bounded environment must prevent reads as an infra checklist.
Reality
- Evidence24
- Adoption
- Not scored
- Hype gap+12
- Incentives68
- Confidence41
buildOne report1 publisher Agent Memory Is Two Systems, Not One Dial With Scratch On One End
A dev.to series on harness engineering splits persistence into in-task scratch and cross-session recall, and argues that building them as one system produces neither.
Reality
- Evidence28
- Adoption
- Not scored
- Hype gap+16
- Incentives62
- Confidence47
buildOne report1 publisher The payload is rebuilt every turn, so stop treating your prompt as a shipped artifact
A dev.to series argues "prompt engineering" is too narrow for agents: the package sent to the model is reassembled on every call, which makes it a runtime concern, not a file.
Reality
- Evidence30
- Adoption
- Not scored
- Hype gap+20
- Incentives65
- Confidence33
buildOne report1 publisher Instrumentation Is the Whole Gap Between an Agent and an Agent You Can Run
A dev.to series argues non-deterministic, multi-step agents cannot be operated on the request-level logging most teams already have. The argument holds, and the work it implies is unglamorous.
Reality
- Evidence24
- Adoption
- Not scored
- Hype gap+18
- Incentives72
- Confidence38