Skip to content

Add beginner's guide to testing agents blog post#16107

Merged
Radu-Raicea merged 31 commits intomasterfrom
feat/blog-testing-agents
Apr 3, 2026
Merged

Add beginner's guide to testing agents blog post#16107
Radu-Raicea merged 31 commits intomasterfrom
feat/blog-testing-agents

Conversation

@Radu-Raicea
Copy link
Copy Markdown
Member

@Radu-Raicea Radu-Raicea commented Mar 31, 2026

Changes

Blog post about how to test agents.

Checklist

  • I've read the docs and/or content style guides.
  • Words are spelled using American English
  • Use relative URLs for internal links
  • I've checked the pages added or changed in the Vercel preview build

@Radu-Raicea Radu-Raicea requested review from a team and ivanagas March 31, 2026 19:54
@github-actions
Copy link
Copy Markdown
Contributor

github-actions bot commented Mar 31, 2026

Deploy preview

Status Details Updated (UTC)
🟢 Ready View preview Apr 03, 2026 01:14PM

@Radu-Raicea Radu-Raicea marked this pull request as ready for review March 31, 2026 19:55
@github-actions
Copy link
Copy Markdown
Contributor

github-actions bot commented Mar 31, 2026

Vale prose linter → found 8 errors, 95 warnings, 1 suggestions in your markdown

Full report → Copy the linter results into an LLM to batch-fix issues.

Linter being weird? Update the rules!

contents/blog/8-learnings-from-1-year-of-agents-posthog-ai.mdx — 5 errors, 14 warnings, 0 suggestions
Line Severity Message Rule
3:11 warning 'learnings' is a possible misspelling. PostHogBase.Spelling
20:219 error Hi, Andy here... use an en dash ( – ) with spaces. On Mac, holding down the Option and hyphen key will give you an en dash. PostHogBase.EnDash
22:245 warning Capitalize 'Feature Flags' for PostHog's product. Use 'feature flags' for the general industry concept. PostHogBase.ProductNames
22:263 warning Capitalize 'Experiments' for PostHog's product. Use 'experiments' for the general industry concept. PostHogBase.ProductNames
22:301 error Hi, Andy here... use an en dash ( – ) with spaces. On Mac, holding down the Option and hyphen key will give you an en dash. PostHogBase.EnDash
34:198 warning Use '[Rr]eact' instead of 'ReAct'. Vale.Terms
37:105 warning 'Goedecke' is a possible misspelling. PostHogBase.Spelling
39:19 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
41:13 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
55:53 warning 'Shhh' is a possible misspelling. PostHogBase.Spelling
57:27 warning 'subagents' is a possible misspelling. PostHogBase.Spelling
59:84 warning 'subagents' is a possible misspelling. PostHogBase.Spelling
61:80 error Hi, Andy here... use an en dash ( – ) with spaces. On Mac, holding down the Option and hyphen key will give you an en dash. PostHogBase.EnDash
61:218 warning 'Subagents' is a possible misspelling. PostHogBase.Spelling
77:180 warning 'cfmp' is a possible misspelling. PostHogBase.Spelling
77:238 error Hi, Andy here... use an en dash ( – ) with spaces. On Mac, holding down the Option and hyphen key will give you an en dash. PostHogBase.EnDash
77:276 warning 'offerred' is a possible misspelling. PostHogBase.Spelling
113:1 error Hi, Andy here... use an en dash ( – ) with spaces. On Mac, holding down the Option and hyphen key will give you an en dash. PostHogBase.EnDash
119:138 warning Capitalize 'Experiments' for PostHog's product. Use 'experiments' for the general industry concept. PostHogBase.ProductNames
contents/blog/best-open-source-llm-observability-tools.md — 0 errors, 49 warnings, 0 suggestions
Line Severity Message Rule
41:220 warning Capitalize 'Session Replay' for PostHog's product. Use 'session replay' for the general industry concept. PostHogBase.ProductNames
41:255 warning Capitalize 'Feature Flags' for PostHog's product. Use 'feature flags' for the general industry concept. PostHogBase.ProductNames
41:288 warning Capitalize 'Experiments' for PostHog's product. Use 'experiments' for the general industry concept. PostHogBase.ProductNames
41:317 warning Capitalize 'Error Tracking' for PostHog's product. Use 'error tracking' for the general industry concept. PostHogBase.ProductNames
41:356 warning Capitalize 'Surveys' for PostHog's product. Use 'surveys' for the general industry concept. PostHogBase.ProductNames
72:4 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
74:2 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
76:1 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
76:72 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
80:6 warning 'What makes Langfuse special?' heading should be in sentence case, and product names should be capitalized. PostHogBase.SentenceCase
80:17 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
82:1 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
84:41 warning 'LLMOps' is a possible misspelling. PostHogBase.Spelling
86:1 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
92:4 warning 'Opik' is a possible misspelling. PostHogBase.Spelling
94:1 warning 'Opik' is a possible misspelling. PostHogBase.Spelling
96:1 warning 'Opik' is a possible misspelling. PostHogBase.Spelling
100:17 warning 'Opik' is a possible misspelling. PostHogBase.Spelling
110:114 warning 'Traceloop' is a possible misspelling. PostHogBase.Spelling
112:1 warning 'Traceloop' is a possible misspelling. PostHogBase.Spelling
114:68 warning 'DBs' is a possible misspelling. PostHogBase.Spelling
114:162 warning 'Traceloop' is a possible misspelling. PostHogBase.Spelling
130:87 warning Capitalize 'Experiments' for PostHog's product. Use 'experiments' for the general industry concept. PostHogBase.ProductNames
130:270 warning 'Arize' is a possible misspelling. PostHogBase.Spelling
132:1 warning 'Arize' is a possible misspelling. PostHogBase.Spelling
140:6 warning 'Opik' is a possible misspelling. PostHogBase.Spelling
142:7 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
146:4 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
148:2 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
148:244 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
150:22 warning 'Mintlify' is a possible misspelling. PostHogBase.Spelling
156:17 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
158:1 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
160:65 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
160:169 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
164:44 warning Capitalize 'Product Analytics' for PostHog's product. Use 'product analytics' for the general industry concept. PostHogBase.ProductNames
164:63 warning Capitalize 'Session Replay' for PostHog's product. Use 'session replay' for the general industry concept. PostHogBase.ProductNames
164:92 warning Capitalize 'Feature Flags' for PostHog's product. Use 'feature flags' for the general industry concept. PostHogBase.ProductNames
165:62 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
166:57 warning 'Opik' is a possible misspelling. PostHogBase.Spelling
169:92 warning 'Helicone' is a possible misspelling. PostHogBase.Spelling
177:92 warning Capitalize 'Feature Flags' for PostHog's product. Use 'feature flags' for the general industry concept. PostHogBase.ProductNames
211:22 warning Capitalize 'Product Analytics' for PostHog's product. Use 'product analytics' for the general industry concept. PostHogBase.ProductNames
233:127 warning Capitalize 'Product Analytics' for PostHog's product. Use 'product analytics' for the general industry concept. PostHogBase.ProductNames
233:148 warning Capitalize 'Session Replay' for PostHog's product. Use 'session replay' for the general industry concept. PostHogBase.ProductNames
244:175 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
244:188 warning 'Opik' is a possible misspelling. PostHogBase.Spelling
251:211 warning 'Langfuse' is a possible misspelling. PostHogBase.Spelling
261:13 warning Capitalize 'Error Tracking' for PostHog's product. Use 'error tracking' for the general industry concept. PostHogBase.ProductNames
contents/blog/stop-ai-slop.md — 1 errors, 10 warnings, 0 suggestions
Line Severity Message Rule
31:43 warning 'eval' is a possible misspelling. PostHogBase.Spelling
41:126 warning Use American English. Use 'judgment' instead of 'judgement'. PostHogBase.AmericanEnglish
54:124 warning 'AInception' is a possible misspelling. PostHogBase.Spelling
57:4 warning 'Why use evals? A tale of two math problems' heading should be in sentence case, and product names should be capitalized. PostHogBase.SentenceCase
60:158 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
62:9 warning 'disguting' is a possible misspelling. PostHogBase.Spelling
82:127 warning 'eval' is a possible misspelling. PostHogBase.Spelling
82:174 warning 'defintely' is a possible misspelling. PostHogBase.Spelling
85:74 error 'are' is repeated! Vale.Repetition
125:36 warning 'upsell' is a possible misspelling. PostHogBase.Spelling
138:18 warning 'eval' is a possible misspelling. PostHogBase.Spelling
contents/blog/testing-ai-agents.md — 0 errors, 6 warnings, 0 suggestions
Line Severity Message Rule
66:116 warning 'reactively' is a possible misspelling. PostHogBase.Spelling
83:71 warning 'Levenshtein' is a possible misspelling. PostHogBase.Spelling
119:70 warning 'Levenshtein' is a possible misspelling. PostHogBase.Spelling
164:241 warning 'eval' is a possible misspelling. PostHogBase.Spelling
166:57 warning 'eval' is a possible misspelling. PostHogBase.Spelling
166:161 warning Use the Oxford comma before 'and' or 'or' in a list of three or more items. PostHogBase.OxfordComma
contents/newsletter/building-ai-features.md — 2 errors, 16 warnings, 1 suggestions
Line Severity Message Rule
52:286 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
64:31 warning Capitalize 'Surveys' for PostHog's product. Use 'surveys' for the general industry concept. PostHogBase.ProductNames
70:64 error Hi, Andy here... use an en dash ( – ) with spaces. On Mac, holding down the Option and hyphen key will give you an en dash. PostHogBase.EnDash
80:12 warning 'Whitworth' is a possible misspelling. PostHogBase.Spelling
213:101 warning 'dogfooding' is a possible misspelling. PostHogBase.Spelling
237:12 warning 'Kalm' is a possible misspelling. PostHogBase.Spelling
239:63 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
241:70 warning Capitalize 'Error Tracking' for PostHog's product. Use 'error tracking' for the general industry concept. PostHogBase.ProductNames
241:114 warning Capitalize 'Feature Flags' for PostHog's product. Use 'feature flags' for the general industry concept. PostHogBase.ProductNames
265:31 warning 'Rahul' is a possible misspelling. PostHogBase.Spelling
265:37 warning 'Vohra' is a possible misspelling. PostHogBase.Spelling
269:156 error Hi, Andy here... use an en dash ( – ) with spaces. On Mac, holding down the Option and hyphen key will give you an en dash. PostHogBase.EnDash
277:139 warning Capitalize 'Session Replay' for PostHog's product. Use 'session replay' for the general industry concept. PostHogBase.ProductNames
279:136 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
291:103 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
295:154 warning Capitalize 'Workflows' for PostHog's product. Use 'workflows' for the general industry concept. PostHogBase.ProductNames
307:181 warning Capitalize 'Experiments' for PostHog's product. Use 'experiments' for the general industry concept. PostHogBase.ProductNames
309:16 warning 'Vanagas' is a possible misspelling. PostHogBase.Spelling
309:96 suggestion Prefer 'proper nouns or they' over 'he'. PostHogBase.Inclusivity

Copy link
Copy Markdown
Contributor

@ivanagas ivanagas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looking solid, left some initial comments, will do another review pass.

Comment thread contents/blog/beginners-guide-to-testing-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md
Comment thread contents/blog/testing-ai-agents.md
Comment thread contents/blog/testing-ai-agents.md
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md
Comment thread contents/blog/testing-ai-agents.md Outdated
@Radu-Raicea Radu-Raicea requested a review from ivanagas April 1, 2026 17:26
Copy link
Copy Markdown
Contributor

@ivanagas ivanagas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looking good, a bunch of copy edits but basically good to go (I'll do one final read through before approval).

Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment on lines +26 to +30
It all begins with the classic "Hello World", though now it's wrapped inside an SDK for creating agents, and suddenly we're not saluting the world, but rather being a helpful assistant.

You work hard tweaking that system prompt, choosing the right model, and changing the available tools and their descriptions until the agent successfully completes your happy paths and edge cases.

Once you're ready, you ship your agent to production and start rolling it out to your users.
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we can just be more explicit about testing just being manual at this stage, but if you have advice for doing this well, it would be nice to include it.

Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md Outdated
Comment thread contents/blog/testing-ai-agents.md
ivanagas and others added 15 commits April 2, 2026 18:44
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Radu-Raicea and others added 9 commits April 2, 2026 14:53
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
@Radu-Raicea Radu-Raicea requested a review from ivanagas April 2, 2026 21:23
Copy link
Copy Markdown
Contributor

@ivanagas ivanagas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

looks good now, good to merge whenever you're ready

@Radu-Raicea Radu-Raicea enabled auto-merge (squash) April 3, 2026 13:02
Co-authored-by: Ian Vanagas <34755028+ivanagas@users.noreply.github.com>
@Radu-Raicea Radu-Raicea merged commit 463b275 into master Apr 3, 2026
19 checks passed
@Radu-Raicea Radu-Raicea deleted the feat/blog-testing-agents branch April 3, 2026 13:14
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants