--- title: "Keep an episode and guest index so AI preps interviews with show history" description: "Record your episode catalog, guest history, show format, and sponsor terms in files so AI preps guests and plans episodes from what your show already covered." canonical: "https://scalewithsearch.com/articles/ai-for-podcast-hosts" date: "2026-01-28" modified: "2026-09-25" --- ## Site navigation - [Scale With Search](https://scalewithsearch.com/) - Real estate - Real estate - [Real estate](https://scalewithsearch.com/for/real-estate) - Work - Start here - [Send your brief](https://scalewithsearch.com/work#send-your-brief) - [Prepare your six-question brief](https://scalewithsearch.com/work#prepare-your-six-question-brief) - Build - [Site build, content library with SEO, signal desk](https://scalewithsearch.com/work) - For your business - Trades and home services - [Auto body and collision shops](https://scalewithsearch.com/for/auto-body-and-collision-shops) - [Foundation and home repair contractors](https://scalewithsearch.com/for/foundation-and-home-repair) - [Garage door and fencing contractors](https://scalewithsearch.com/for/garage-door-and-fencing-contractors) - [HVAC contractors](https://scalewithsearch.com/for/hvac-contractors) - [Janitorial and commercial cleaning companies](https://scalewithsearch.com/for/janitorial-and-commercial-cleaning) - [Locksmiths](https://scalewithsearch.com/for/locksmiths) - [Moving companies](https://scalewithsearch.com/for/moving-companies) - [Pest control companies](https://scalewithsearch.com/for/pest-control-companies) - [Plumbing and electrical contractors](https://scalewithsearch.com/for/plumbing-and-electrical-contractors) - [Restoration and water or fire damage companies](https://scalewithsearch.com/for/restoration-and-water-fire-damage) - [Roofing companies](https://scalewithsearch.com/for/roofing-companies) - [Towing companies](https://scalewithsearch.com/for/towing-companies) - [Tree services and landscaping companies](https://scalewithsearch.com/for/tree-services-and-landscaping) - [Solar installers](https://scalewithsearch.com/for/solar-installation) - [General contractors](https://scalewithsearch.com/for/general-contractors-and-construction) - [Paving, concrete, and flooring contractors](https://scalewithsearch.com/for/paving) - Practices and professional services - [Bookkeeping and tax practices](https://scalewithsearch.com/for/bookkeeping-and-tax-practices) - [Dental practices](https://scalewithsearch.com/for/dental-practices) - [Family and criminal defense law firms](https://scalewithsearch.com/for/family-and-criminal-defense-law-firms) - [Med spas and aesthetics practices](https://scalewithsearch.com/for/med-spas-and-aesthetics) - [Personal injury law firms](https://scalewithsearch.com/for/personal-injury-law-firms) - [Veterinary clinics](https://scalewithsearch.com/for/veterinary-clinics) - [Gyms and fitness studios](https://scalewithsearch.com/for/fitness) - [Therapy and outpatient health practices](https://scalewithsearch.com/for/therapy-and-outpatient-health) - [Medical billing companies](https://scalewithsearch.com/for/medical-billing) - [Insurance agencies](https://scalewithsearch.com/for/insurance-agencies) - [Financial advisors](https://scalewithsearch.com/for/financial-advisors) - [Property management companies](https://scalewithsearch.com/for/property-management) - [Recruiting and staffing agencies](https://scalewithsearch.com/for/recruiting-and-staffing) - [Architects and interior designers](https://scalewithsearch.com/for/architects-and-interior-designers) - [Logistics and supply chain companies](https://scalewithsearch.com/for/logistics-and-supply-chain) - Agencies, MSPs, and manufacturing - [IT and managed service providers](https://scalewithsearch.com/for/it-and-managed-service-providers) - [Machine shops and precision manufacturers](https://scalewithsearch.com/for/machine-shops-and-precision-manufacturing) - [Marketing agencies and freelancers](https://scalewithsearch.com/for/marketing-agencies-and-freelancers) - [SEO agencies and consultants](https://scalewithsearch.com/for/seo-agencies-and-consultants) - [Small manufacturers and fabricators](https://scalewithsearch.com/for/small-manufacturers-and-fabricators) - Restaurants, shops, studios, and nonprofits - [Restaurants and hospitality businesses](https://scalewithsearch.com/for/restaurants-and-hospitality) - [Retail stores and ecommerce sellers](https://scalewithsearch.com/for/retail-and-ecommerce) - [Photographers, event planners, and travel agents](https://scalewithsearch.com/for/photographers) - [Churches and nonprofits](https://scalewithsearch.com/for/churches-and-nonprofits) - [All industries](https://scalewithsearch.com/for/) - Learn - For your office - [Office job guides](https://scalewithsearch.com/guides/) - [Browser calculators](https://scalewithsearch.com/tools/) - Start here - [How it works](https://scalewithsearch.com/how-it-works) - [Free Starter Kit](https://scalewithsearch.com/kit/business-memory-starter-kit.zip) - [Synthetic specimen](https://scalewithsearch.com/specimen/working-session-specimen.zip) - Guides - [The Complete Guide to Business Memory for AI Agents](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [The Complete Small-Business Guide to AI Agent Governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [The Complete Guide to Leaving Vendor AI Memory](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - Articles by cluster - [Business memory](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [Agent governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [Migration and ownership](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - For machines - [llms.txt](https://scalewithsearch.com/llms.txt) - [llms-full.txt](https://scalewithsearch.com/llms-full.txt) - [Machine view](https://scalewithsearch.com/?view=machine) - Company - Evidence - [Proof](https://scalewithsearch.com/proof) - Company - [About](https://scalewithsearch.com/about) # Keep an episode and guest index so AI preps interviews with show history. A host prepares episode 127. The AI assistant does not know what happened in episode 126 or who was on the show last month. It does not know which topics came up twice this year. Each session starts blank. A podcast builds context over time: guest preferences, topic clusters, sponsor terms, and show structure. A general assistant treats each conversation as the first one. The host spends the first ten minutes of every session explaining the format, the audience, and the goal. Long sessions also lose detail as the conversation grows, so the useful stretch is short. An episode index, a guest file, and a sponsor file put that context in a record the assistant reads first. The sections below show what each file holds and how to use it for guest prep, episode planning, and sponsor tracking. ## Why a show needs a record A podcast is a body of work, not a series of separate episodes. It has recurring guests, ongoing themes, and audience expectations built over dozens or hundreds of recordings. Without a record, continuity breaks. You cannot reference past conversations, compare guest views, or avoid covering the same ground. Guest prep becomes manual: dig through old notes, transcripts, and email, then paste fragments into a chat and hope the assistant connects them. A chat's working memory is not the same as a record. The guide on [context window vs persistent AI memory](/articles/context-window-vs-persistent-ai-memory) explains what survives the next session and what does not. ## What the files hold | File | Contents | |---|---| | `show.md` | Format, audience, segment structure, intro variations, standard questions, interview style, depth of research your audience expects | | `episodes.md` | One entry per episode: number, date, guest, topics, key moments, links to earlier episodes on the same topic | | `guests.md` | One entry per guest: public background with sources, past appearances, questions that worked, topics that fell flat, where the last conversation ended | | `sponsors.md` | Each active sponsor: read length, key messages, placement, excluded categories, reads due, episode fit, performance notes | ## Inspect the guest file This is a synthetic entry. ```markdown # guests.md ## Guest G-14 (synthetic) role:: founder, logistics software company sources:: company site; two recent interviews (links in /research/G-14/) appearances:: ep 88 (2025-03), ep 121 (2026-06) ## What worked - Story of the first warehouse client: long, specific answer. - Question on hiring the first operations lead. ## What fell flat - Industry forecast questions: short, generic answers. ## Where the last conversation ended - Ep 121: said the company would test a new pricing model "this fall". Follow-up: ask how the test went. ## Updates since last appearance - 2026-08: announced a second office. source:: company blog post ``` The `sources::` line matters. Guest research from the assistant can include false details. Keep each claim about a guest tied to a public source, and check it before you say it on air. ## Load the files each session Claude Code reads a file named `CLAUDE.md` from the working folder when a session starts ([Claude Code memory documentation](https://code.claude.com/docs/en/memory), checked 2026.09.25). Put the contents of `show.md` there, and list where the other files live. Then ask for the job. The files stay on your computer, but the text Claude Code reads goes to Anthropic for processing. Retention and training terms depend on your plan. Keep guests' private contact details and unreleased sponsor terms out of the files unless your agreements allow it. ## Prepare guest research that fits the show Most hosts research guests the same way each time. They scan the website, check social accounts, read recent work, and compile questions. It takes an hour or more per guest, and half of it goes to finding the angle. With the files, you give the assistant a guest name and your sources. It knows your focus areas and your format. It finds connection points to earlier episodes and suggests question angles that fit. For a returning guest, it shows what worked last time, what did not, and where the conversation stopped. The next interview builds on the last one instead of repeating it. Recurring guests gain the most. The file tracks their projects, updates, and changing views between appearances. When they return, you pick up a conversation that has history. ## Plan episodes from the catalog Some hosts record freeform. Others use outlines. Either way, planning needs to know what you already covered, what your audience responds to, and how the next episode fits the larger plan. With `episodes.md`, the assistant can show topic clusters. If you did five episodes on productivity and one on delegation, it flags the imbalance. If a new guest's expertise overlaps with an earlier interview, it names the episode so you can refer to it on air. Solo episodes can develop across several sessions. Sketch an outline in one session, refine it in another, and finalize it before you record. The draft outline lives in a file, so it does not reset between sessions. ## Produce show notes from the format Show notes need your timestamp style, quotes in your voice, and links in the format your audience expects. With `show.md`, the assistant has the template. Give it a transcript, and it returns formatted notes. Timestamps sit where you want them, sections follow your order, and sponsor mentions land in the right place. The same format rules apply to clips, email summaries, and episode descriptions. The companion guide on [AI for podcasters](/articles/ai-for-podcasters) covers show notes and social posts in your voice in more depth. For how to keep a transcript's evidence apart from its summary, see [AI memory for interview transcripts](/articles/ai-memory-interview-transcripts-summaries). ## Track sponsor terms and fit Sponsors have requirements: read length, key messages, placement, and categories they exclude. With several sponsors across episodes, tracking them becomes administrative work. `sponsors.md` records each sponsor once. When you plan an episode, the assistant knows which sponsors are active and which reads are due. For dynamic ad insertion, it knows which sponsors fit which episode types. An interview with a financial expert may conflict with one sponsor and suit another. The file makes that visible before you record. Record performance over time: which reads drove results and which placements did best. That record supports renewal talks and new sponsor pitches. Disclose paid sponsorship on air as the FTC endorsement rules require, and keep that disclosure line in the sponsor entry. ## Test the files before the next recording Run three checks in a fresh session. 1. Ask "Prep me for G-14's return." Pass: the prep names the pricing test from episode 121 as the first follow-up and lists the second office announcement with its source. Fail: a generic bio and generic questions. 2. Ask "Which episodes covered delegation?" Pass: the episode numbers from `episodes.md`. Fail: the assistant invents an episode, or answers from general knowledge. 3. Ask "Which sponsor reads are due for the next episode?" Pass: the reads and their required messages from `sponsors.md`. Fail: it lists a sponsor the file marks as ended. A fail on the first check means the guest entry lacks a "where the last conversation ended" section. Add one for every returning guest. ## Set the limits The assistant researches, plans, and drafts. You decide what goes on air and what gets published. It does not contact guests, accept sponsor terms, or publish notes. When a research claim has no source, it must say so. ## Set up the files in two hours 1. Write `show.md`: format, audience, recurring segments, standard questions, interview style. 2. Add the last 20 episodes to `episodes.md` from your publishing platform. 3. Add every guest from the past year to `guests.md`, with what worked. 4. Add active sponsors and their terms to `sponsors.md`. 5. Ask for prep on your next guest and compare it with your own notes. After that, log each new episode, add guest notes after each interview, and refine the format rules when a draft misses. For research that spans many episodes, the guide to [AI memory for content research](/articles/ai-memory-content-research) shows how to keep sources and rejected angles between sessions. ---- ```text .|########||. .|########||. .|########||. |##||. .||##|. |##||. .||##|. |##||. .||##|. |#|. .|#|. |#|. .|#|. |#|. .|#|. |#| |#| |#| |#| |#| |#| .#| |#. .#| |#. .#| |#. .#. .#| .#. .#| .#. .#| |#. .#| |#. .#| |#. .#| |# ...... #| |# ...... #| |# ...... #| .# ||#########| #| .# ||#########| #| .# ||#########| #| .#. |######||######|. .#. .#. |######||######|. .#. .#. |######||######|. .#. #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# # .||####|###########################|. # # .||####|###########################|. # # .||####|###########################|. # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || #. .######|#|#########| .# #. .######|#|#########| .# #. .######|#|#########| .# .#. |#####||||#####| .#. .#. |#####||||#####| .#. .#. |#####||||#####| .#. |# ||########|| #. |# ||########|| #. |# ||########|| #. |# ...... #| |# ...... #| |# ...... #| |#. .#| |#. .#| |#. .#| |#. .#. |#. .#. |#. .#. .#| |#. .#| |#. .#| |#. |#| |#| |#| |#| |#| |#| .|#|. .|#|. .|#|. .|#|. .|#|. .|#|. |##||. .||##| |##||. .||##| |##||. .||##| .||########||. .||########||. .||########||. Scale With Search 2026 [scalewithsearch.com](https://scalewithsearch.com) ```