27 July 2026

 

    New AI model lineup: OpenAI’s GPT-5.6 tiers, xAI’s Grok 4.5, Anthropic’s Claude 5 family, Google’s Gemini 3.6/3.5 Flash updates, Perplexity’s agents, and leading open-weight models all add better reasoning, multimodality, and flexible pricing.

    Genealogy impact now: Longer context windows and stronger multimodal tools make it easier to process big probate, land, pension, and county-history bundles in one pass, while Perplexity and NotebookLM improve citation-backed search, structured notes, timelines, and teaching materials.

    Ready-to-use workflows: The briefing lists 25 concrete micro-workflows—from conflict-resolution memos and surname abstracts to cemetery-photo transcription, land-chain tables, and privacy-friendly batch extraction—each tied directly to a specific new model or feature release

 Implications for genealogists this week

25 July 2026

 

    Workflow agents emerge: ChatGPT Work, Sites, and Perplexity Brain/Computer now turn chat-style assistance into full research pipelines, from source images to finished reports and web pages.

    Cheaper, faster models: New Gemini Flash variants, Grok 4.5 pricing, and evolving open-weight long-context models lower the cost of batch tasks like census extraction, deed abstracting, and large case-file review.

    Genealogy-ready 22 concrete AI workflows—spanning census transcription, deed and probate analysis, cemetery cleanup, and cross-tool proof arguments—explicitly tied to each new release.

24 July 2026

• Default model shake-up: OpenAI dropped GPT-4.5 from ChatGPT in favor of GPT-5.5 Instant as default; Google's Gemini 3.5 Flash now powers AI Mode and Search agents worldwide.

• Shift from tools to agents: Google is building Gemini into a multi-agent, task-oriented layer within Search; Canva and Adobe are embedding deeper conversational AI into their creative/design workflows.

23 July 2026

 AI platform shifts: OpenAI is rolling out ChatGPT Work and Sites, along with improved cross-device sync, voice, dictation, and spreadsheet integrations. Meanwhile, Google and Anthropic are focusing on more agentic, multi-step, and personalized workflows.

New AI releases: Google launched Gemini 3.6 Flash and 3.5 Flash-Lite; OpenAI rolled out GPT-5.6 Sol while scheduling the retirement of GPT-4.5 and o3; and Perplexity, xAI, and various open-weight models expanded the field of options.

Genealogy impact:

22 jULY 2026

 

 Google on Tuesday released three new models, including Gemini 3.6 Flash, its most powerful, and Gemini 3.5 Flash Cyber, which is fine-tuned for cybersecurity.

OpenAI refreshed ChatGPT with new desktop Work mode, larger custom instructions, better search, GPT-Live-1 voice, and Sites for dashboards and light apps.

Google AI search changes: Google’s AI Mode now runs on Gemini 3.5 Flash with multimodal search, web-monitoring agents, and custom dashboards that can watch sources and personal files.    

Workflow continuity gains: ChatGPT Work and Perplexity’s July Computer update help genealogists keep context across files, notes, and drafts, streamlining movement between records, analysis, and writing. 

 Reasoning vs speed: New tiers like GPT-5.6 Sol/Terra/Luna and Grok 4.5, plus fast modes in Perplexity, let researchers match deeper proof arguments to high-reasoning models while using cheaper, quicker variants for triage and cleanup.

Open-weight and governance: Anthropic’s HIPAA tools and system messages, Kimi K3’s huge multimodal context, and updated open-source leaders support privacy-conscious long-form projects and signal the need to update workflows before older ChatGPT models retire.

21 July 2026

T he July 19–21 landscape is specifically defined by GPT‑5.6, Claude Fable 5, Gemini 3.5 Flash, Grok 4.5, and the current model+agent portfolios those providers now expose.

  Frontier models mature: GPT‑5.6, Claude Fable 5, Gemini 3.5 Flash, Grok 4.5 and updated open‑weight models now target complex, multi‑step reasoning—ideal for county‑ or tribe‑level research projects.

    Context tiers stabilize: Gemini 3.1 Pro and similar large‑window models can ingest full county histories or multi‑volume files, while cheaper tiers like GPT‑5.6 Luna or Flash‑Lite handle bulk chores such as transcription, tagging and data cleaning.

    Agentic workflows expand: New features like Claude Agent Teams and broader model+agent harnesses let you run coordinated “transcriber,” “planner” and “citation checker” agents, enabling at least 20 plug‑and‑play micro‑workflows tailored to genealogists.

20 examples tied to this week’s releases

Below are ready‑to‑run micro‑workflows you can test today, each linked conceptually to at least one of the new/updated models or agent capabilities above. You can implement them in ChatGPT (GPT‑5.6), Claude (Fable 5 / Opus 4.8), Gemini, Grok, Perplexity, or an open‑weight stack like DeepSeek/Llama depending on what you have.fazm+3

1. County history super‑digest (Gemini 3.1 Pro + 3.5 Flash)

   • Load a full county history PDF (300–600 pages) into Gemini 3.1 Pro, ask it to extract all occurrences of your surname clusters, migration paths, and church or tribal affiliations, then pass the extracted notes to Gemini 3.5 Flash for a concise research memo and to‑do list.mean+2

2. Probate packet triage (GPT‑5.6 Sol + Luna)

   • Use GPT‑5.6 Luna (cheap tier) to transcribe and lightly summarize each document in a large probate packet, then send the summaries to GPT‑5.6 Sol to identify heirs, land descriptions, relationships, and conflicting evidence for formal research notes.fazm+2

3. Civil War pension conflict table (Claude Fable 5 + Opus 4.8)

   • Feed multiple pension affidavits and service records to Claude Fable 5 and ask for a “conflict table” outlining name, unit, dates, residence, and claims; then use Claude Opus 4.8 to suggest targeted record sets (regimental histories, local newspapers, county court minutes) to resolve each conflict.fazm+2

4. Five Tribes enrollment strategy planner (Perplexity + Claude Fable 5)

   • In Perplexity, ask for a sourced overview of Dawes Rolls, tribal censuses, and Oklahoma/Indian Territory land records for a specific tribe; then paste that context into Claude Fable 5 and have it propose a step‑by‑step research plan tailored to your ancestor’s dates and locations.perplexity+2youtube

5. Mass census extraction with open‑weights (DeepSeek V4 or Llama 4)

   • Run a folder of OCR’d census pages (e.g., a township) through a local DeepSeek or Llama 4 pipeline to extract heads of household, ages, birthplaces, and occupations, and output a CSV you can import into RootsMagic or Excel for neighborhood analysis.devflokers+2

6. Neighborhood cluster mapping (GPT‑5.6 Terra + mapping tool)

   • Paste a table of extracted households from several censuses into GPT‑5.6 Terra and ask it to identify recurring surname clusters, kin networks, and likely FAN (Friends/Associates/Neighbors) candidates, then generate a list of land plats or city directories to check for each cluster.promptzone+2

7. AI‑guided local history scan (Gemini 3.5 Flash)

   • Use Gemini 3.5 Flash’s stable agentic abilities to scan digitized local histories, church anniversary booklets, or school bulletins, asking it to flag any mention of your target surname plus approximate years and places, and create a citation‑ready table.claude-world+2

8. Image‑heavy record review (Grok 4.5)

   • With Grok 4.5’s strong web and coding abilities, feed screenshots of online trees, census images, and land descriptions, asking it to cross‑check details against live web sources and highlight obvious errors or unsupported leaps in online trees.mean+3

9. Cemetery transcription & analysis (Claude Sonnet/Haiku + Agent Teams)

   • Use a fast model like Claude Haiku or Sonnet inside an Agent Teams setup: one agent transcribes headstones from photos, another normalizes names/dates, and a third suggests likely family groupings and missing burials based on age patterns and plot proximity.claude-world

10. Clustered town directory clean‑up (GPT‑5.6 Luna + Terra)

    • Run a large batch of OCR’d city directory pages through GPT‑5.6 Luna to extract names, addresses, and occupations; then send the messy table to GPT‑5.6 Terra to standardize addresses, infer duplicate individuals, and prepare a “follow‑up research” sheet.fazm+2

11. Research log normalization (any frontier model)

    • Paste a messy multi‑year research log into Claude Fable 5, GPT‑5.6 Sol, or Gemini 3.5 Flash and ask it to deduplicate entries, normalize citation formats, and group work by question (“Identify parents of X,” “Prove identity of Y in 1860 vs 1870 census”).fazm+3

12. Land chain of title narrative (Gemini 3.1 Pro)

    • Feed a long sequence of deeds, mortgages, and probate sales to Gemini 3.1 Pro with the instruction to build a chain‑of‑title narrative for one parcel, including owner sequences, relationship notes, and links to census and tax records for each owner.mean+2

13. “FAN club agent shop” (Claude Agent Teams)

    • Define three Claude agents: “Transcriber” (extracts names, places, dates from records), “FAN Builder” (groups by recurring associates), and “Hypothesis Mapper” (turns clusters into migration or kinship hypotheses); let Agent Teams coordinate them over a targeted set of records.claude-world

14. Oklahoma Territory research scaffold (Perplexity + GPT‑5.6)

    • Ask Perplexity for a current, sourced summary of Oklahoma Territory record types and availability by county and year; then use GPT‑5.6 Sol to convert that into a checklist for one ancestor, with columns for “searched,” “not yet searched,” and “not extant.”youtubeperplexity+3

15. Multi‑volume church minutes reader (Gemini + Claude)

    • Combine Gemini 3.1 Pro’s large context with Claude Fable 5’s judgment: Gemini digests several volumes of church minutes (names, discipline cases, membership changes), then Claude builds timelines for your target surname and suggests additional record sets (membership rolls, local newspapers, civil court).fazm+3

16. Cross‑platform source sanity check (Grok 4.5 + Perplexity)

    • When an online tree makes a bold claim (e.g., “this ancestor is on a particular roll”), capture the screen, feed it to Grok 4.5 to extract the assertion, and then ask Perplexity to pull current, sourced discussion of that roll and whether the claim is plausible given dates and geography.perplexity+4

17. Narrative creation from scattered notes (Claude Fable 5)

    • Paste years of scattered research notes on one ancestor into Claude Fable 5 and ask it to assemble a chronological life narrative, marking uncertain points explicitly and generating a separate “research plan” section to resolve each uncertainty.fazm+2

18. Record set discovery for under‑used sources (GPT‑5.6 Sol)

    • Use GPT‑5.6 Sol to brainstorm under‑used record types for a specific county and time (road orders, school censuses, tax duplicates, poorhouse registers), then filter that list through Perplexity or Gemini for which are digitized and where to access them.perplexity+4

19. Local, privacy‑sensitive research notebook (Llama 4 / DeepSeek V4)

    • Run a local Llama 4 or DeepSeek V4 model and point it at your private research notes in Markdown; ask it to flag unresolved questions, contradicting evidence, and missing citations without sending anything to a cloud provider.devflokers+2

20. Weekly “AI genealogy stand‑up” (any portfolio)

    • Once a week, open your main AI tool (Claude, ChatGPT with GPT‑5.6, Gemini, Grok, or Perplexity) and paste a short list of ongoing research problems; have it propose the next three actions per problem, tag which tasks are suited to frontier vs. cheaper tiers, and note which require human archive work.

 

20 July 2026

The emergence of GPT‑5.6 across ChatGPT means you now have a new “top tier” long‑form reasoning engine for tasks like locality research write‑ups, complex land/probate correlation, and multi‑document analysis, but at higher token costs—so it’s worth consciously choosing when you really need Sol versus cheaper Terra or Luna. Because GPT‑5.2 models have been retired from ChatGPT, any saved workflows or prompts that referenced those specific models should be refreshed to target 5.6 variants to avoid confusion and to calibrate for new response behavior.

On the Anthropic side,

18 July 2026 - What Wctually Changed this Week and What To Do With It

Here’s your compact, “what actually changed this week and what to do with it” briefing for working genealogists and family historians based on releases and trackers updated through July 17–18, 2026.

---

A. Named releases & features (last ~72 hours + still hot)

• Moonshot AI – Kimi K3 (frontier, open-weight, long‑context)
  New reasoning‑focused model released July 16, 2026 with strong performance on long documents and complex analysis, positioned as a frontier‑level open‑weight option.[aireleasetracker]

• OpenAI – GPT‑5.6 family (Sol, Terra, Luna) GA in APIs and ChatGPT
  The full GPT‑5.6 line moved from staged rollout to broad availability in early–mid July, with Luna as the smallest, cheaper model and Sol/Terra as larger reasoning models.[llm-stats]

• OpenAI – GPT‑5.6 Luna pricing + long‑context adjustments
  Luna is priced around $1 per million input tokens and $6 per million output, part of an updated pricing structure that makes extended context (128k+) more affordable.[kersai]

• OpenAI – GPT‑5.6 Sol/Terra (research‑grade reasoning)
  Sol and Terra are higher‑capacity models aimed at deep research, multi‑document synthesis, and more reliable complex reasoning, now fully available in production.[llm-stats]

• OpenAI – GPT‑Live full‑duplex voice rollout (still expanding)
  GPT‑Live, OpenAI’s real‑time, full‑duplex voice assistant built on GPT‑5.x, continues rolling out; it allows conversational exploration of research, timelines, and sources via voice.[skycrumbs]

• OpenAI – GPT‑5 Mini updates (better structure/output)
  The lightweight GPT‑5 Mini tier got upgraded weights in early July with improved instruction‑following and structured output, useful for fast, cheap list‑building and checklists.[skycrumbs]

• OpenAI – Open‑weight models gpt‑oss‑120b and gpt‑oss‑20b (recent)
  OpenAI has introduced two open‑weight models (gpt‑oss‑120b and gpt‑oss‑20b), giving researchers and tool builders high‑quality models whose weights can be hosted and customized.[help.openai]

• Anthropic – Claude Sonnet 5 (new mainline model, late June but “current”)
  Claude Sonnet 5 landed at the end of June and is now a primary, widely‑used model with strong narrative, summarization, and long‑context capabilities.[llm-stats]

• xAI – Grok 4.5 (reasoning + lower prices)
  Grok 4.5 launched around July 8, 2026 and is priced at roughly $2 per million input tokens and $6 per million output, with a focus on reasoning and high‑throughput workloads.[llm-stats]

• Meta – Muse Spark 1.1 (multimodal, model API)
  Muse Spark 1.1, released July 9, 2026, exposes a public API for a multimodal model good at images and text, adding another strong option for integrated document + image workflows.[aireleasetracker]

• Google – Gemini 1.5 Pro (1M‑token context, multimodal)
  Gemini 1.5 Pro, already in wide release by mid‑2026, offers a 1‑million‑token context window, fast generation, and strong multimodal support; it remains an important long‑context tool this week.[howdoiuseai]

• Open-weight – Kimi K2/K3 line (frontier‑level open models)
  Moonshot’s Kimi series (K2 previously, K3 now) represent open‑weight models that match or exceed proprietary models in reasoning and long‑context tasks, giving self‑hosters serious options.[llmgateway]

• Open-weight – GLM 5.x (coding/agentic support, strong open baseline)
  GLM 5.x (and specifically 5.2) is positioned as a leading open‑weight model with strong coding and agent support, often used as the engine behind custom AI genealogy helpers.[openrouter]

• Perplexity – Research‑focused AI search (ongoing, but critical for this week)
  Perplexity continues to operate as a real‑time, citation‑backed AI search engine with a freemium model, widely used for up‑to‑date research and “where are the records now?” questions.[howdoiuseai]

• ChatGPT platform – Deep Research, Record Mode, memory & connectors
  The current ChatGPT platform bundles deep multi‑source research, meeting transcription/summary (Record Mode), persistent memory, and 60+ app connectors—including Google Drive and Slack—into one environment.[howdoiuseai]

• Gemini – Thinking/transcription modes for long, handwritten documents
  Gemini’s current generation (often referenced as “Gemini 3.0” in genealogy usage guides) adds improved thinking modes and handwriting‑friendly transcription, particularly useful for deeds and wills.[denyseallen.substack]

• Claude – Tool‑using assistant with long‑document timelines
  Claude’s tool‑use features and strong timeline generation capabilities make it a natural choice for converting long narrative genealogical documents into clean chronological timelines.[youtube][marketingaiinstitute]

• Family history AI ecosystem – FamilySearch AI Research Assistant (ongoing)
  FamilySearch’s AI Research Assistant uses modern LLMs to provide guided record‑finding, summarization, and translation within FamilySearch’s ecosystem, and continues to be updated.[youtube][familysearch]

• Pricing landscape – Cheaper long‑context across frontier and open‑weight
  Across GPT‑5.6, Grok 4.5, Muse Spark 1.1, Kimi K3, and others, prices per million tokens for long‑context reasoning have dropped, making multi‑document uploads and long projects more economically viable.[kersai]

---

B. Implications for genealogists this week

For working genealogists, the big story is that long‑context reasoning just got cheaper and more widely available across both proprietary and open‑weight models. That means you can realistically feed an entire locality study, multi‑generation timeline, or a full probate packet into a single session and ask for structured analysis, instead of chopping everything into tiny pieces.[rauljitechnologies]

At the same time, models are differentiating by role: ChatGPT (GPT‑5.6) for planning and structured workflows, Perplexity for citation‑backed “where are the records now?”, Gemini for transcription and multimodal document work, Claude for timelines and narrative polish, and Grok/Kimi/GLM for those who want open‑weight or lower‑cost custom agents. You benefit by matching the task to the model instead of trying to force one tool to do everything.[openrouter]

Finally, the new GPT‑Live and improved smaller models (GPT‑5 Mini, Luna) make lightweight, conversational, “always‑on” assistance more practical, especially for routine tasks like checklist generation, quick record‑type reviews, and voice‑driven brainstorming while you’re looking at microfilm or digitized images. Combined with FamilySearch’s AI assistant and other domain‑specific tools, you now have an ecosystem where you can move seamlessly from “What records should exist?” to “Where are they?” to “What do they say?” to “How do I write this up?” inside coordinated AI workflows.[familysearch][youtube]

---

C. Plug‑and‑play AI micro‑workflows you can try today

Below are at least twenty concrete, current, genealogy‑specific workflows tied explicitly to the named releases/features above. I’ll assume you’re comfortable moving between tools; each item is one self‑contained “micro‑workflow” you can run as a small experiment.[familysearch][youtube]

1–5: Long‑context case files with GPT‑5.6 and Gemini

1. Probate packet deep read (GPT‑5.6 Sol/Terra)
   Upload a multi‑document probate file (petition, inventory, accounts, distributions) to ChatGPT powered by GPT‑5.6 Sol or Terra and ask for:

   • A chronological timeline of events

   • List of all named individuals with roles (executor, heir, creditor)

   • A summary of property categories (land, livestock, household goods)
     Use the cheaper long‑context pricing to keep the entire packet in one run.[huggingface]

2. Locality guide synthesis (GPT‑5.6 Luna + Perplexity)
   First ask GPT‑5.6 Luna in ChatGPT for a “record‑type checklist” for, say, Oklahoma Territory circa 1890–1907 (land, probate, court, tribal, etc.). Then paste each record type into Perplexity and ask, “Where can I access [record type] for [county/time] today?” to get up‑to‑date repositories and URLs with citations.[skycrumbs]

3. Multi‑family cluster reconstruction (Gemini 1.5 Pro)a
   Load a large batch of census pages and city directory scans into Gemini 1.5 Pro’s long‑context environment, and ask it to:

   • Identify all households with the target surname

   • Flag recurring neighbors and addresses

   • Suggest possible cluster families based on proximity and shared occupations.[aireleasetracker]

4. Handwritten deed transcription (Gemini “thinking” mode)
   For a hard‑to‑read handwritten land deed, upload the image to Gemini and use its advanced transcription/thinking mode to produce a text version. Ask follow‑ups: “Extract grantor, grantee, legal description, consideration, witnesses, and dates in a simple table.”[youtube][familysearch]

5. Narrative source comparison (GPT‑5.6 Sol + Claude Sonnet 5)
   Use GPT‑5.6 Sol to produce a structured comparison of several conflicting birth records (church register, delayed certificate, family Bible) in a table (source, date, informant, reliability notes). Then send that table to Claude Sonnet 5 and ask it to draft a narrative “evidence summary” paragraph using genealogical proof‑style language.[marketingaiinstitute][youtube]

6–10: Timelines, conflict tables, and research planning

6. Automated ancestor timeline (Claude Sonnet 5)
   Paste a long, existing narrative biography plus extracts from key records into Claude Sonnet 5 and ask: “Convert this into a chronological timeline of dated events, with columns for event, date, place, source, and notes.”[youtube][rauljitechnologies]

7. Research conflict matrix (Claude + GPT‑5 Mini)
   In ChatGPT using GPT‑5 Mini, quickly list all conflicting claims about an ancestor (birth years, parents, residences) and format them as a rough table. Paste that table into Claude Sonnet 5 and ask it to expand into a full conflict matrix with reliability assessment and “next steps” research questions.[marketingaiinstitute][youtube]

8. County‑level research plan (ChatGPT GPT‑5.6 Luna)
   Ask ChatGPT with GPT‑5.6 Luna: “Act as a genealogy research planner. Create a 4‑week research plan for tracing land and probate records for [county] in [time period], including archives, catalog searches, and likely record series.” Use the improved structured‑output to get tasks grouped by week.[skycrumbs]

9. Multi‑generation migration path (GPT‑5.6 Terra + Gemini maps/images)
   Provide GPT‑5.6 Terra with a list of locations and dates for a family across several censuses and land records. Ask it to infer migration routes and possible transportation corridors. Then use Gemini to generate a simple, labeled map illustration you can include in your report or blog.[familyhistorystorytelling.wordpress]

10. Cluster research brainstorming (Grok 4.5)
    Feed Grok 4.5 a description of a “brick‑wall” ancestor and the cluster around them (neighbors, associates, witnesses). Ask it to propose at least ten cluster‑based research avenues (church membership lists, school records, occupational guild files, etc.), ranking them by probability and effort.[familysearch]

11–15: Record‑finding and repository work

11. Where‑are‑the‑records map (Perplexity + GPT‑5.6)
    Take your location and time period, ask GPT‑5.6 Luna in ChatGPT for a list of possible record types (civil registration, court minutes, tax rolls). Then, for each record type, ask Perplexity “Where are [record type] for [county/state, years] currently accessible?” and save the cited URLs into Zotero.[denyseallen.substack]

12. FamilySearch AI Research Assistant scouting
    Use FamilySearch’s AI Research Assistant to ask, “Show me potential records for [ancestor] in [region], and summarize why each is relevant,” then immediately test those suggestions against your own hypothesis. Treat it as a scout, not an oracle.[youtube][familysearch]

13. Catalog mining via ChatGPT connectors
    With ChatGPT’s connectors to Google Drive or similar, upload an exported catalog search result (CSV or PDF) from a state archive and ask GPT‑5.6 Luna to:

    • Group entries by record series (deeds, judgments, probate)

    • Flag series that directly mention your surnames

    • Suggest a visit plan (which boxes to pull first).[howdoiuseai]

14. Open‑weight “agent” that knows your locality (GLM 5.x or Kimi K3)
    If you run your own stack, fine‑tune GLM 5.x or Kimi K3 on a set of locality guides, catalog entries, and your own notes for a single county. Use that agent to answer “Given this research question, which five specific record series in this county should I prioritize?”[openrouter]

15. Repository contact drafts (Claude Sonnet 5)
    Paste a description of the records you need and repository details into Claude Sonnet 5, and ask it to draft concise, polite email templates to archivists or county clerks, including call numbers or series names.[marketingaiinstitute][youtube]

16–20: Transcription, photos, and narrative

16. Batch transcription triage (Gemini + Claude)
    Before investing in full transcriptions, upload a bundle of images (probate, land, church registers) to Gemini and ask it only for “keyword extraction” (surnames, place names, occupations). Use those keywords to decide which images go to the front of your queue, then send the most promising items to Claude for full narrative summaries.[youtube][marketingaiinstitute]

17. Photo set clustering and caption help (Muse Spark 1.1)
    Use Muse Spark 1.1 to analyze a group of digitized family photos, asking it to cluster images by setting (farm, town, school) and approximate era from clothing/vehicles. Then prompt for suggested neutral captions (“Two unidentified children in rural setting, circa 1910s”) to store in your photo database.[familysearch]

18. Life‑story draft from scattered notes (Claude Sonnet 5 + GPT‑5.6)
    Combine scattered research notes into one long document and feed it to Claude Sonnet 5 for a first‑pass narrative biography. Then ask GPT‑5.6 Sol to convert that biography into a research‑style “proof summary” organized by identity, parentage, and migration, citing each claim back to a source list you provide.[rauljitechnologies][youtube]

19. Voice‑driven research brainstorming (GPT‑Live)
    Use GPT‑Live via voice while looking at digitized microfilm or working in a reading room. Talk through your current brick wall and ask it to suggest concrete next steps (“three record types in this county I haven’t checked”), capturing the audio or notes as a Saturday‑morning briefing.[huggingface]

20. Automated research log clean‑up (GPT‑5 Mini / Luna)
    Export your research log from Zotero, Excel, or RootsMagic as CSV. Ask GPT‑5 Mini or Luna to normalize repository names, flag duplicate searches, and generate a short “this week’s priorities” list based on unresolved items and high‑value record series.[ancestorsandai.buzzsprout]

21–24: Advanced/open‑weight experiments

21. High‑volume surname sweep (Grok 4.5 or Kimi K3)
    If you have a large, text‑based dataset (OCR’d newspapers, tax rolls, court minutes), send it in chunks to Grok 4.5 or Kimi K3 and ask for a structured extraction of all instances of a surname with date/place; then merge into a master spreadsheet.[kersai]

22. Custom “probate explainer” bot (GLM 5.x open‑weight)
    Fine‑tune GLM 5.x on a curated set of probate case studies and glossaries. Use it locally as a bot that explains obscure probate terms or procedures in plain language while you’re abstracting wills or estate files.[openrouter]

23. Language‑heavy parish record analysis (Gemini + Claude)
    For non‑English parish registers, run first‑pass transcription and translation via Gemini. Then give Claude Sonnet 5 the translated text and ask it to identify naming patterns, godparent clusters, and possible extended kin groups.[familysearch][youtube]

24. “Evidence table” generator across tools (Perplexity + GPT‑5.6)
    Use Perplexity to gather up‑to‑date secondary sources on a local event (e.g., land run, epidemic, migration wave) that affected your ancestor’s locality. Then feed those citations plus your primary sources into GPT‑5.6 Terra and ask it to produce a table showing how each source supports or contradicts your current hypothesis.[aigenealogyinsights]