Sensors and Guides: Two Ways Your Harness Talks to Your Agent
The article discusses the importance of balancing guides and sensors in harness engineering for agents. Guides help shape the agent's behavior before output is produced, while sensors provide feedback after the fact. Neglecting either can lead to predictable failure modes, highlighting the need for both in effective agent management.
- ▪Guides are elements that influence an agent's behavior before it generates output, such as rules files and example code.
- ▪Sensors detect issues in the agent's output after it has been produced, including tools like linters and tests.
- ▪A reliance on only guides can lead to rule fatigue, while a focus solely on sensors may result in slow feedback loops.
DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV.to (Top) |
| Canonical URL | https://dev.to/tacoda/sensors-and-guides-two-ways-your-harness-talks-to-your-agent-39oh |
| Publication time | Fri, 22 May 2026 20:17:48 +0000 |
| Retrieval time | 2026-05-22T20:32:02.974Z |
| Last seen | 2026-05-22T20:32:02.974Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | b7RHX73QPf4a |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 171498) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Ian Johnson Posted on May 22 Sensors and Guides: Two Ways Your Harness Talks to Your Agent #ai #productivity #programming #agents Birgitta Böckeler, writing about harness engineering at Thoughtworks, draws a distinction that turns out to be more useful than it first appears: a harness contains guides and sensors. Guides point the agent toward correct behavior up front. Sensors catch the agent after the fact, when it has produced something that does not meet the bar.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
