Wekelijkse samenvatting van AI-onderwerpen

[Discourse]

Overview

This week’s AI conversations on Meta centered on making Discourse AI clearer to users and easier to operate at scale. On the product side, there was strong momentum to rename “AI Persona” to the more widely understood “AI Agent” (with translation workflow implications) in Renaming AI Persona → AI Agent and follow-ups like Renaming AI Persona → AI Agent. Admin experience also got attention: sites with AI disabled were still seeing AI dashboards/reports, which was confirmed as a bug and routed into broader reporting work in Don’t show AI reports if AI is not enabled and the related umbrella thread Admin Reporting & Analysis: Incremental Changes.

Operationally, the community dug into cost/performance controls and scaling pain points: Discourse rolled out OpenAI/Azure provider service tiers in Service tiers on Open AI providers, while a large self-hosted instance reported severe load when turning on semantic embeddings search in Enabling AI search crippled my server. There was also continued refinement around AI-assisted UX—especially where AI touches localization and editor UI—in Saving translations by AI-helper as content localization and The title suggester button is placed outside of the title field when editing a translated title.

Finally, AI adjacent ecosystem work continued with MCP tooling: a practical setup guide landed for Codex CLI in Discourse MCP Setup in OpenAI Codex CLI, and was cross-linked back into the canonical announcement thread Discourse MCP is here!.

---

Interesting Topics

• Rename “AI Persona” to “AI Agent” (and handle the translation fallout)
  sam argued that “AI Persona” is confusing while “AI Agent” is broadly understood in Renaming AI Persona → AI Agent, with Falco backing an ASAP change in Renaming AI Persona → AI Agent. Moin raised the practical issue of updating lots of translations and asked about efficient translator workflows in Renaming AI Persona → AI Agent and Renaming AI Persona → AI Agent, while sam pressed for whether the terminology aligns with industry usage across languages in Renaming AI Persona → AI Agent.

• Bug: AI emotion/sentiment reports appear even when AI is disabled (bug, ai-sentiment)
  one1 spotted AI-related reports showing up on the admin dashboard with AI turned off in Don’t show AI reports if AI is not enabled, and sam confirmed it’s a bug in Don’t show AI reports if AI is not enabled. chapoi noted it’s part of a broader “all plugins” reporting visibility issue, and routed follow-up feedback into Admin Reporting & Analysis: Incremental Changes (see also Admin Reporting & Analysis: Incremental Changes).

• OpenAI/Azure provider “service tiers” added (cost vs latency controls) (#Announcements, ai)
  Discourse shipped the ability to pick service tiers (standard/flex/priority) for OpenAI and Azure in Service tiers on Open AI providers, and pointed admins to the core configuration surface in Discourse AI - Large Language Model (LLM) settings page. The announcement also clarified reliability tradeoffs (especially flex) in Service tiers on Open AI providers.

• UX bug: title-suggester star button mispositioned for translated titles (ux, ai-helper, content-localization)
  Moin reported the AI “” title suggester button renders outside the title input when editing a translated title in The title suggester button is placed outside of the title field when editing a translated title, with repro context pointing at translation UI states (example thread: Request for Croatian language).

• Feature idea: let AI Helper save a generated translation into Content Localization (#Feature, ai-helper, dynaloc)
  After using AI Helper to translate older posts, Moin proposed a “save translation” flow right from the helper modal in Saving translations by AI-helper as content localization, suggesting parity with AI Helper’s “explain → add footnote” pattern as precedent in Saving translations by AI-helper as content localization.

• Mobile UX regression around Suggested/Related tabs (AI suggested topics UI) (ux, suggested-topics)
  Falco noticed the tabs disappearing on mobile and asked if it’s related in The underline indicator below the “Suggested” and “Related” tabs. awesomerobot confirmed it is related and pointed to an incoming fix in The underline indicator below the “Suggested” and “Related” tabs.

• Theme component maintenance: AI Gists button compatibility with Modernized Foundation (#Theme-component, ai)
  Lilly refactored a theme component so formatting works with Modernized Foundation while keeping compatibility with the old Foundation theme in Discourse Topic Excerpts & AI Gists Button, tying into the broader theme effort in Modernizing the Foundation theme.

• Performance/scaling: semantic embeddings search triggering high CPU and backlog (Support, ai-search)
  A large instance reported search disruption and sustained CPU spikes after enabling semantic search in Enabling AI search crippled my server. sam explained that long-running embedding jobs can be expected due to external API calls, but that high CPU is surprising and likely tied to DB/resource constraints in Enabling AI search crippled my server. Falco asked for provider and DB details in Enabling AI search crippled my server, while SubStrider shared specs and dataset size (2.5M posts / 250K topics) in Enabling AI search crippled my server. rburkej also requested more “hardware profile” info for planning self-hosting in Enabling AI search crippled my server.

• MCP tooling: Codex CLI setup guide for Discourse MCP (users, mcp)
  pacharanero published a step-by-step guide for using Discourse MCP with OpenAI Codex CLI in Discourse MCP Setup in OpenAI Codex CLI and linked it back into the main announcement thread in Discourse MCP is here!.

• Permissions hardening: Discourse AI bot groups shouldn’t allow “everyone” (bug, ai-bot)
  In the ongoing thread, Moin asked whether the “everyone” group should be disallowed for ai_bot_allowed_groups in Discourse AI does not respect the “everyone” group, and sam agreed it should be removed (noting cleanup work planned) in Discourse AI does not respect the “everyone” group.

---

Activity

• sam drove several core decisions and debugging threads this week: pushing hard on terminology clarity in Renaming AI Persona → AI Agent and aligning language/translation concerns in Renaming AI Persona → AI Agent; confirming the admin dashboard issue in Don’t show AI reports if AI is not enabled; shipping provider tier controls in Service tiers on Open AI providers (with configuration context via Discourse AI - Large Language Model (LLM) settings page); and troubleshooting embeddings performance in Enabling AI search crippled my server. He also backed tightening AI bot group options in Discourse AI does not respect the “everyone” group.

• Moin focused on localization + AI UX polish: raising translation workflow concerns for the proposed rename in Renaming AI Persona → AI Agent and clarifying Crowdin complications in Renaming AI Persona → AI Agent; reporting a translated-title UI glitch in The title suggester button is placed outside of the title field when editing a translated title (with a real-world translation context example in Request for Croatian language); proposing a workflow improvement to persist AI Helper translations in Saving translations by AI-helper as content localization; and suggesting permissions hardening around “everyone” for AI bot allowed groups in Discourse AI does not respect the “everyone” group.

• Falco reinforced product direction and helped triage UX/perf: endorsing the terminology switch in Renaming AI Persona → AI Agent; flagging mobile behavior changes in The underline indicator below the “Suggested” and “Related” tabs; and requesting deeper environment details to diagnose load in Enabling AI search crippled my server.

• one1 raised an admin-facing quality issue: AI sentiment/emotion reports appearing with AI disabled in Don’t show AI reports if AI is not enabled, which helped confirm a bug and consolidate feedback into the broader reporting workstream in Admin Reporting & Analysis: Incremental Changes.

• chapoi provided important context that the reporting visibility issue extends beyond AI to all plugins, and redirected follow-up discussion into the main reporting thread via Don’t show AI reports if AI is not enabled and Admin Reporting & Analysis: Incremental Changes.

• SubStrider shared a concrete scaling report from a large forum, including a clear “semantic search → CPU spike → search disruption” sequence in Enabling AI search crippled my server, and later provided hardware specs and corpus size details for diagnosis in Enabling AI search crippled my server.

• rburkej added a self-hosting perspective by asking for a detailed hardware profile and operational impact notes in Enabling AI search crippled my server, reinforcing that semantic search rollout needs clear sizing guidance.

• pacharanero advanced the MCP ecosystem by publishing a tested Codex CLI setup guide in Discourse MCP Setup in OpenAI Codex CLI and then cross-linking it into the main MCP announcement thread in Discourse MCP is here!.

• Lilly kept AI-adjacent theming healthy by refactoring a component so the AI Gists button formatting works on Modernized Foundation in Discourse Topic Excerpts & AI Gists Button, tying the work to the upstream theme direction in Modernizing the Foundation theme.

• awesomerobot confirmed the mobile tabs disappearance was related to the “Suggested/Related” UI changes and noted a fix was incoming in The underline indicator below the “Suggested” and “Related” tabs.

• NateDhaliwal closed the loop on an AI-assisted tagging annoyance by acknowledging a fix for an error popup in Error popup when suggesting tags in topic already having tags.

• jdc20181 shared progress on automation work that leverages AI-assisted development: porting a Python script into a Discourse plugin to move topics based on triggers (including scheduled automation) in Creating a system to move topics based on given criteria such as a timestamp.

In total (last 7 days): 6 new topics and 25 posts, with the heaviest engagement around naming/UX polish and practical scaling/cost controls for embeddings and OpenAI usage—see Renaming AI Persona → AI Agent, Service tiers on Open AI providers, and Enabling AI search crippled my server.

Thanks for reading, and I’ll see you again next week!

[Discourse]

Overview

Over the past week (2026-03-09 → 2026-03-16), Meta’s ai discussions clustered around product polish, reliability, and “real world” operations.

On the product side, Discourse moved closer to standardizing terminology by implementing the rename from AI Persona to AI Agent (Renaming AI Persona → AI Agent). On the infrastructure side, Discourse significantly expanded capacity for its hosted LLM offering—raising limits across all tiers and improving model quality and latency characteristics (Unlock All Discourse AI Features with Our Hosted LLM).

Meanwhile, operators focused on how AI fits into community rhythms: a request to delay AI Agent replies (so they feel less like a chatbot and more like a participant) surfaced both as a new Support topic (Adding a configurable delay to AI Agent responses) and as a follow-up in the longer-running “Agents” guide thread, where Discourse staff indicated that delayed responses would likely belong in a future automation overhaul rather than ai itself (AI bot - Agents).

Integration conversations had a notable bump too: Google’s Programmable Search / Custom Search constraints and deprecations are forcing a rethink of web search tooling, with Discourse exploring alternative providers and even “native search tools” from LLM vendors (Google Search for Discourse AI - Programmable Search Engine and Custom Search API). In parallel, community guides continued to expand around the Discourse MCP ecosystem, including a newly posted OpenCode CLI setup walkthrough (Discourse MCP Setup in OpenCode CLI).

Finally, practical admin workflows came up repeatedly: improving observability for AI spam detection via direct database queries (Discourse AI - Spam detection), questions about sentiment analysis backfilling and debugging (Problems setting up Sentiment), and GDPR-oriented concerns about sentiment processing depending on provider/configuration (Introducing Discourse AI Sentiment Analysis: New Admin Report Available). There was also an open Support thread (in Chinese) on tool-call timeouts, still in the “need more details” stage (Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？).

---

Interesting Topics

• “AI Persona” renamed to “AI Agent” (terminology + implementation) in #Feature ai. Falco confirmed the rename work landed and pointed to the corresponding PR (Renaming AI Persona → AI Agent).

• Hosted LLM capacity increased dramatically (plus model + performance upgrades) in #Announcements ai. Discourse reported higher plan limits across the board and described improvements like updated “state-of-the-art open weights” model, higher max tokens per request, better tokens/sec, and improved time-to-first-token (Unlock All Discourse AI Features with Our Hosted LLM).

• Delaying AI Agent responses to match community pacing (1–4 hours) in Support ai. saurabhmithal asked for a configurable delay so Agents feel less like instant chatbots (Adding a configurable delay to AI Agent responses). In the broader “Agents” thread, Falco clarified it’s not possible today and positioned it as an automation capability, hinting at early planning for a major automation overhaul (AI bot - Agents); the original request is captured in-thread too (AI bot - Agents).

• Google Programmable Search / Custom Search friction and deprecation pressures in #Integrations how-to ai. Ethsim2 hit a new UI constraint requiring at least one configured site, which disables “search the entire web” (Google Search for Discourse AI - Programmable Search Engine and Custom Search API). Falco then stated Google discontinued the feature and noted Discourse is researching alternative providers and also planning support for “native web search tools” offered by major LLM providers (Google Search for Discourse AI - Programmable Search Engine and Custom Search API).

• Community alternatives for web search tooling (Searxng + privacy realities) in #Integrations ai. satonotdead recommended self-hosting Searxng and argued it’s a pragmatic response to tightening restrictions across major platforms (Google Search for Discourse AI - Programmable Search Engine and Custom Search API). Lilly also flagged broader platform shifts (Custom Search JSON API being replaced in Google’s ecosystem) as a sign documentation may need updates (Google Search for Discourse AI - Programmable Search Engine and Custom Search API).

• Discourse MCP setup guidance expands (OpenCode CLI) in users ai mcp. pacharanero posted a tested guide for installing Discourse MCP into OpenCode CLI, emphasizing that users can even point an LLM at the guide URL to help with setup (Discourse MCP Setup in OpenCode CLI). The guide cross-links to the Codex CLI variant for other MCP clients (Discourse MCP Setup in OpenAI Codex CLI).

• AI spam detection: custom instructions, reporting desires, and “show me the raw logs” in #Site_Management moderation ai. LotusJeff shared a more detailed (token-heavier) spam detection instruction set and asked what others use (Discourse AI - Spam detection). They also asked for deeper reporting behind the admin summary box and whether Data Explorer could expose the details (Discourse AI - Spam detection). Falco replied with a direct query against ai_spam_logs and referenced the Data Explorer tool itself (Discourse AI - Spam detection, Data Explorer).

• Sentiment analysis backfill expectations (automatic 60 days) vs. historical needs in Support ai-sentiment. satonotdead asked about backfilling sentiment for a long-running self-hosted community and hit a rake task warning (“Don’t run this task in production!”) (Problems setting up Sentiment). Falco clarified that enabling the feature automatically backfills the last 60 days (Problems setting up Sentiment) and later pointed to the self-hosting setup guide as the baseline for debugging (Problems setting up Sentiment, Self-Hosting Sentiment and Emotion for DiscourseAI).

• Sentiment debugging details: “allowed internal hosts” and job execution in Support ai-sentiment. satonotdead reported resolving part of the issue by adding an internal IP to allowed internal hosts, then manually running Jobs::SentimentBackfill but still wanting complete historical backfill (Problems setting up Sentiment). Falco asked for clarification about whether at least the 60-day data appeared (Problems setting up Sentiment), and satonotdead confirmed dashboards work but the historical backfill is still the goal (Problems setting up Sentiment).

• GDPR/compliance questions for AI sentiment analysis in #Announcements ai-sentiment. jackierenee asked how sentiment data is processed for Europe-based orgs and whether enabling it can be GDPR compliant (Introducing Discourse AI Sentiment Analysis: New Admin Report Available). awesomerobot noted it depends on configuration and provider, and recommended seeking local legal advice rather than expecting legal determinations on Meta (Introducing Discourse AI Sentiment Analysis: New Admin Report Available).

• Tool invocation timeout troubleshooting (needs clearer repro details) in Support ai. shixiaochi reported Operation timed out - FinalDestination::HTTP and asked whether Discourse timeouts can be adjusted (Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？). Falco repeatedly asked which tool/request is timing out, while the OP added screenshots but hadn’t yet provided the exact tool name or repro steps (Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？, Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？, Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？, Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？).

---

Activity

• Falco drove several key updates and support replies this week: confirmed the rename work landed in Renaming AI Persona → AI Agent; announced major service scaling in Unlock All Discourse AI Features with Our Hosted LLM; explained that delayed Agent responses aren’t available and likely belong to future automation work in AI bot - Agents; provided a Data Explorer-ready SQL snippet for spam logs in Discourse AI - Spam detection (building on the reporting question in Discourse AI - Spam detection); clarified sentiment’s automatic 60-day backfill in Problems setting up Sentiment and pointed troubleshooting back to docs in Problems setting up Sentiment; and pushed for a clearer repro in the timeout thread Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？ and Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？. He also shared the state of play on Google web search tooling and future alternatives in Google Search for Discourse AI - Programmable Search Engine and Custom Search API.

• pacharanero published a new end-user setup guide for MCP, walking through installation and configuration in Discourse MCP Setup in OpenCode CLI and pointing readers to the Codex variant when using other clients (Discourse MCP Setup in OpenAI Codex CLI).

• saurabhmithal raised the “make Agents feel human-paced” request in a dedicated Support topic—Adding a configurable delay to AI Agent responses—and also asked the question within the longer-running guide thread (AI bot - Agents), prompting clarification that this is currently more an automation feature request than ai (AI bot - Agents).

• Ethsim2 reported an up-to-date Google UI constraint affecting Discourse AI’s documented setup, specifically around requiring at least one configured site and disabling “search the entire web,” in Google Search for Discourse AI - Programmable Search Engine and Custom Search API.

• Lilly added context that Google’s Custom Search JSON API appears to be getting superseded by newer Google offerings, implying docs may need revision, in Google Search for Discourse AI - Programmable Search Engine and Custom Search API.

• satonotdead contributed on two fronts: suggested Searxng as a practical alternative for web search in Google Search for Discourse AI - Programmable Search Engine and Custom Search API; and dug into sentiment backfill limitations and debugging, including the production rake warning (Problems setting up Sentiment), lack of initial data visibility (Problems setting up Sentiment), the “allowed internal hosts” fix plus manual job execution (Problems setting up Sentiment), and confirmation that dashboards now work but historical backfill is still needed (Problems setting up Sentiment).

• LotusJeff shared a more detailed custom instruction set for AI spam detection (Discourse AI - Spam detection) and asked for more granular reporting / Data Explorer options behind the admin summary metrics (Discourse AI - Spam detection).

• jackierenee raised a practical compliance question for EU orgs—how sentiment data is processed and whether enabling the feature can be GDPR compliant—in Introducing Discourse AI Sentiment Analysis: New Admin Report Available.

• awesomerobot responded to the GDPR question by emphasizing that compliance depends on configuration and the selected AI provider, and recommended seeking local legal guidance (Introducing Discourse AI Sentiment Analysis: New Admin Report Available).

• shixiaochi opened a Support thread describing Discourse AI tool-call timeouts (FinalDestination::HTTP) (Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？), then followed up with screenshots while the thread worked toward a clearer identification of which tool/request is failing (Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？, Discourse ai 的工具调用超时如何解决？是否可以调整discourse超时时间，如何调整？).

• flysto_ryan appeared in the MCP ecosystem thread via a (now deleted) reply in the Codex CLI setup topic (Discourse MCP Setup in OpenAI Codex CLI).

---

Thanks for reading, and I’ll see you again next week!