Field Notes by Oleg GaidukovTechnical decisions, trade-offs, and operating lessons from Oleg Gaidukov's work.https://ovg.me/AI product risk lives in the gray zonehttps://ovg.me/field-notes/ai-psychology-gray-zone-risk/https://ovg.me/field-notes/ai-psychology-gray-zone-risk/Why a plausible answer is not enough when the product must detect ambiguity and stop the normal flow.Fri, 07 Aug 2026 00:00:00 GMTTwo roadmaps make fresh code feel like legacyhttps://ovg.me/field-notes/two-roadmaps-instant-legacy/https://ovg.me/field-notes/two-roadmaps-instant-legacy/What a repository reveals when the team's real planning horizon is shorter than the official product plan.Wed, 29 Jul 2026 00:00:00 GMTAn AI transformation needs an ownerhttps://ovg.me/field-notes/ai-transformation-owner/https://ovg.me/field-notes/ai-transformation-owner/Acceleration language means little until one person owns the operating boundary and its trade-offs.Wed, 22 Jul 2026 00:00:00 GMTA fractional CTO must not leave an empty chairhttps://ovg.me/field-notes/fractional-cto-empty-chair/https://ovg.me/field-notes/fractional-cto-empty-chair/A fractional mandate works when it transfers ownership instead of renting one person's judgment.Fri, 29 May 2026 00:00:00 GMTThe throughput target no customer neededhttps://ovg.me/field-notes/100k-tps-grave/https://ovg.me/field-notes/100k-tps-grave/A field report about sizing a system for a demand assumption that the business never forced itself to validate.Tue, 19 May 2026 00:00:00 GMTAgents work better as advisorshttps://ovg.me/field-notes/agents-as-advisors/https://ovg.me/field-notes/agents-as-advisors/A practical boundary for agentic engineering when confident automation is still wrong often enough to matter.Fri, 27 Mar 2026 00:00:00 GMT