Menu

Individual skill

podium-rag-context-bridge

0upvotes

Bridge a live Podium call transcript or webchat turn to an LLM by fetching relevant historical conversation context as a structured RAG bundle — vector search over embedded prior conversations + reranking + live Podium contact lookup, merged under a hard latency budget that keeps the call answerable in real time. Use when wiring a transcription-driven agent loop to an LLM that needs cross-channel customer memory, building the substrate that turns "transcript chunk" into "LLM-ready prompt with context", or hardening an existing RAG pipeline against staleness, reranking noise, PII leakage, token-budget overflow, and missed-the-call latency. Trigger with "podium rag", "podium llm context", "podium transcript to llm", "podium retrieval", "podium vector search", "podium real-time context", "podium agent grounding".

plugins/saas-packs/podium-pack/skills/podium-rag-context-bridge/SKILL.md

Read pinned source

Source commit 0500b275e963c027f6b410e8c49c0446945c574e

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 12, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
2,916
Repository last updated
Nov 12, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Podium RAG Context Bridge

## Overview

Take a live transcript chunk (or webchat turn) and emit a structured RAG context bundle the calling LLM can drop into its prompt. This is not a chatbot. This is the substrate that sits between Podium's transcription stream and whatever LLM your agent loop is using — fetching the right historical context, fast enough to matter, in a shape the model can actually consume.

The substrate combines two retrieval surfaces: a **vector store** of past Podium conversations (embedded at ingest by `podium-conversation-history-export`) and a **live Podium API lookup** for the contact's fresh state (phone, opt-out, location, last-seen). The two surfaces answer different questions — vectors answer "what did this person ever say about this topic," the live API answers "is the phone number we're about to dial actually still their phone number." A naive RAG pipeline collapses them and ships drift to the model.

The six production failures this skill prevents:

1. **Relevance scoring picks wrong historical context** — naive cosine similarity over top-K=5 chunks surfaces the five most similar embeddings; on real Podium corpora most of those are off-topic boilerplate ("thanks for reaching out", "have a great day"). The model sees noise, generates a generic reply, and the operator loses the customer. Fix: cross-encoder reranking + per-contact filtering BEFORE the model sees anything.
2. **Vector store stale vs live Podium data drift** — the contact updated their phone yesterday; today the vector store still embeds the old number. The model answers "I'll call you back at (555) 0100" using a number that hasn't worked in 16 hours. Vector recall and live state are different SLAs and must be merged with live state winning on any field that can mutate.
3. **Transcript chunk boundaries lose context** — the transcriber emits chunks every 800ms. A boundary that cuts "my order number is" / "ABC-12345" in half means neither chunk retrieves the order. Both retrieve nothing relevant. Fix: sliding-window overlap (default 200ms tail of previous chunk prepended to the embed query) plus chunk coalescing before embedding.
4. **LLM token budget overflow** — retrieved context plus system prompt plus transcript history pushes the user prompt past the model's window. Most models silently truncate from the middle; some refuse the request. Either way the model is operating on a corrupted prompt. Fix: hard token budget per retrieval surface (default 1500 tokens of context, summarized if over).
Back to top