Fixing an AI phone agent that misjudged business hours
11/21/2026 — 11/21, 02:17·1 sources (all)·1 reports (all)
Key takeaways
- A developer who built an AI phone agent for a home-services company reviewed how a Retell voice agent with an n8n backend failed on real pho…
Background & analysis
On 2026-11-21 at 01:51, the AI section of DEV Community published a retrospective by a developer who builds AI phone agents for home service companies. The piece reviews failure points that appeared once the system was connected to real phone lines, along with the fixes applied.
The setup uses a Retell voice agent to answer incoming calls, while n8n workflows handle the work behind the scenes: checking a calendar, booking appointments, and writing to the CRM. The developer reports that the prompt originally contained the business hours and the current time, yet the model still got the "are we open right now" judgment wrong often enough to matter in practice.
The remedy was to stop asking the model to make that call. An n8n step now works out the answer first and passes it in as a variable, and calendar writes are required to go through an agent that reads the call transcript before writing. The retrospective closes at a summary of these failure points and their corresponding fixes, and the material provides no follow-up data or validation results from after the changes went live.
AI-generated from 1 reports · updated 1 day ago
- Heat index
- 39
- All sources
- 1
- All reports
- 1
- First seen
- 1 day ago
Reports on this story headlines open the original
A developer who builds AI phone agents for home-service companies describes how a Retell voice agent backed by n8n workflows failed on real calls. The model kept getting the open-or-closed call wrong even with business hours and the current time in the prompt, so the rule moved out of the prompt and into an n8n step that passes the answer in as a variable. Calendar writes now go through a proxy that checks the transcript first.
DEV Community · AIAI score 55
Other stories people are talking about
- Heat index 1143RisingAnthropic Reaches $1.6 Trillion Market Value in First Trading Week After IPO21 sources
- Heat index 1011Anthropic Mathematician Says Claude Formalized the Generalized Riemann Hypothesis21 sources
- Heat index 622Anthropic IPO total raise reaches $93.5 billion after greenshoe exercise20 sources
- Heat index 596RisingThinking Machines Lab Open-Sources Inkling 2 Mini with 32GB Model Card Recommendation10 sources
- Heat index 490RisingSEC probes Nvidia accounting practices as shares post seven-week slide9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

