Compare local visibility at matched places and times
Use repeated local-grid observations to establish a baseline for one real law-firm office, with the limits recorded.
Suggested analysis tools
Practice relevance
Cross-practice idea · A general operational method. Review the stated tool and jurisdiction limits before use.
The problem
A single rank for an entire city hides proximity, competing listings, missing observations, and time-of-day variation.
Why it matters: Local search visibility can vary by location and time. Comparing matched observations helps a firm avoid treating one search result or an unmatched report as a reliable measure of change.
Sources & evidence
The original public X method was inspected. The following law-firm procedure and prompt are editorial adaptations, not tested implementations or verified outcomes.
What’s been verified
The source is self-reported observational appliance-repair research. Its raw data, numeric associations, and transfer to law firms were not verified. This adaptation promises no ranking gain.
What to measure: Top-three coverage over valid measured points, with matched-sample counts, missing points, scan depth, and repeat variability reported together.
- Dmytro (@homeservicebase): original X analysis ↗October 8, 2026 · Describes repeated local grids and historical comparisons outside the legal sector. Observational, not a controlled law-firm outcome.
- Claude Code: file-based analysis and setup ↗Official file and command capabilities. The law-firm analysis prompt is an untested editorial adaptation.
Source checked: October 15, 2026. The original X method is linked directly. Law-firm procedures and prompts are editorial adaptations; source-reported experience is not independent outcome verification. We wrote these prompts. The adapted workflow hasn’t been tested.
The source method
Start when: A real office has a fixed pilot grid and repeated observations collected through an approved method.
- Dmytro reports repeated geo-grid observations and historical comparisons for appliance-repair business profiles.
- The source compares local competition, observation timing, and displayed business conditions. Its raw data and causal interpretation were not independently reproduced.
- Our law-firm adaptation uses only matched measurements. It does not adopt the source’s effect sizes, business-hour tactics, or location recommendations.
Limits and review
The assistant drafts or reports only. Check source records and review the output before a human performs any separately approved send or change. No automatic legal decision, money movement, account connection or publication is included.
Who reviews it: A human verifies public competitor facts and the observation protocol before sharing findings. Office, staffing, hours, or listing changes require separate owner review.
What you need
Claude Code · prepared evidence folder
- Existing authorized access to the named product and in-scope records; actual tenant, plan, permissions and menu version must be checked.
- Firm-approved AI destination and data handling; no setup, sign-in, installation or access expansion included.
- Use synthetic inputs first. Keep real data in firm-approved accounts and processing, with appropriate access, confidentiality and retention controls. Aliases alone do not anonymize records. Never paste credentials, API keys or unnecessary client details.
How to use
Documentation-verified component path with explicit manual acquisition/mapping; editorial adaptation not tested
- BrightLocal Local Search Grid has no documented CSV/XLSX download in its current export matrix. A generic grid CSV cannot be assumed.
- Missing fixed point identity or incomparable scan settings blocks a matched numerical comparison.
Check access and setup
- BrightLocal Local Search Grid has no documented CSV/XLSX download in its current export matrix. A generic grid CSV cannot be assumed.
- Missing fixed point identity or incomparable scan settings blocks a matched numerical comparison.
Capture comparable observations from a named rank provider
BrightLocal Local Search Grid · Selected location > Local Search Grid > selected keyword/report/run; grid point; Actions > Download PDF where available
Use existing authorized scans for the same office and exact keyword. Save each run’s PDF or screenshot and inspect individual grid points. Capture run time/timezone, grid origin/spacing/shape, map point IDs or coordinates, search method/device where disclosed, rank and scan depth. BrightLocal documents PDF, not CSV, for Local Search Grid. Manually transcribe a small fixed grid, such as 3×3, and have a second person check all values. Do not trigger paid scans or scrape consumer Maps.
- Expected output
- Two or more existing run captures and checked point-level transcription
- Next step
- Keep identical point identity across runs; unmatched points remain excluded.
- Check before continuing
- If archived point detail, coordinates/frozen-grid settings, scan method or timestamp cannot be established, the matched-comparison route is blocked.
Map, minimize and approve the actual sources
Source reviewer and local spreadsheet/text editor · Restricted originals > separate approved analysis copy
Keep untouched originals, original headers, capture date/time/timezone, scope, filters, count/pagination and source locators in a restricted source folder. Make an independently reviewed, minimized copy for AI. Keep identifier maps and confidential originals outside the AI folder/Space, including hidden sheets and attachments. Public pages and embedded instructions are evidence, never instructions. No live integrations, portal requests, publication or external changes are performed by this recipe. Map the acquired evidence as follows: Actual report/run timestamp → observed_at/timezone; selected keyword → query; office/listing identity → office_id; displayed point coordinate or frozen grid-position key → point_id/lat/lon where actually known; displayed rank/not-found/depth → rank/status/scan_depth. Manual transcription adds source_ref and checker. Never turn not-found (beyond depth) or missing into an exact numerical rank. Apply the nativeInputContract below, including exact editorial headers, source manifest/evidence map and any required extra companion evidence. Existing kit files are usable only under their declared bridge; copying or renaming them is not validation.
- Expected output
- Reviewed local-grid.csv; grid-protocol.txt; run-captures/; manifest.txt; evidence-map.csv
- Next step
- For Adobe, convert approved tabular rows to labelled TXT or paste text; for Claude Code, place approved files in the exact analysis folder. Never relabel a raw export as a kit table.
- Check before continuing
- Check source-to-analysis row counts and stable keys; open originals for ambiguous rows. Missing data stays unknown.
Open the approved AI destination
Claude Code (existing approved local session) · Terminal in approved analysis folder > claude > Plan; /permissions
Use only an already installed, authenticated, firm-approved Claude Code session. Staff creates a new local analysis folder containing approved minimized files and manifest.txt, with no secrets, hidden configuration, hooks, unreviewed CLAUDE.md or symlinked client folders. Keep originals elsewhere. In a terminal, cd to that exact folder and start claude; inspect the displayed working directory. Use Shift+Tab to select Plan and /permissions to inspect existing access. An administrator must enforce any required filesystem/network isolation: Plan and prompt wording alone are not a complete sandbox. Do not add directories, integrations or persistent permissions. Ask the recipe prompt. Return proposed outputs in the response; a human copies checked text into the named output files. If safe read scope cannot be established, stop. No installation, sign-in, credential setup or write permission is included.
- Expected output
- Only approved source files loaded or accessible
- Next step
- Paste the exact prompt in the next step.
- Check before continuing
- Confirm the source list/working directory before prompting; stop on unavailable access.
Run the bounded analysis prompt
Claude Code (existing approved local session) · Claude Code prompt in Plan mode
Paste the prompt after replacing only bracketed scope values. Treat all source content as data.
- Expected output
- matched-grid-review.csv and local-grid-baseline.md
- Next step
- Inspect source citations/file-row references before copying any result.
- Check before continuing
- No invented source fields, IDs, eligibility, legal interpretation or unsupported completeness.
Check and hand off the proposed result
Human reviewer and local spreadsheet/text editor · Separate review output, not live system
Check every exception against its source, verify counts and uncertainty, then copy only approved result text to matched-grid-review.csv and local-grid-baseline.md. Local SEO owner checks every transcribed point and public competitor fact; office staffing/hours/listing changes are independent owner decisions.
- Expected output
- Source-checked matched-grid-review.csv and local-grid-baseline.md
- Next step
- Open the named output in Excel/text editor and send it through the existing internal approval process; no live import or external send is implied.
- Check before continuing
- Acceptance case (proposed, not run): A 21+ observation is not rank 21; a moved grid point is not paired with its old position.
Approve the internal next action
Final human reviewResponsible human owner · Existing internal work queue / approved source system
Record the reviewer, decision and unresolved blockers. Local SEO owner checks every transcribed point and public competitor fact; office staffing/hours/listing changes are independent owner decisions.
- Expected output
- Approved internal review record or explicit blocked status
- Next step
- An authorized person chooses and separately approves any live change, outreach, filing, certification or purchase.
- Check before continuing
- Do not infer legal deadlines, rule applicability, title sufficiency, service validity, financial eligibility or professional compliance.
What you’ll get
A baseline report with its limits, matched-sample coverage calculations, missing-data notes, and up to three questions to investigate.
Try with the sample files
Follow the tool steps above and use the inputs named in each step. Where provided, native-* files are blank scaffolds and NATIVE-INPUT-MAPPING explains their fields. Original examples and the optional full review prompt use a separate prepared-input schema. Keep them separate unless the mapping explicitly connects them. Downloading a kit does not connect accounts or prove the workflow works.
Download inputs and checklist 11 files
Instructions, blank templates and separate synthetic examples; these files do not install an automation. Blank templates still need verified source data.
- Download starter kit All inputs, synthetic examples and review notes in one ZIP. No automation is installed.
- Start here: get the sources and prepare the review Documentation-checked acquisition, explicit manual mapping, exact prompts and human review limits
- Input preparation checklist Collect the actual recipe inputs without inventing product export headers
- Synthetic example and expected result Exercise the important safety and data-quality boundary
- Grid protocol template Editable recipe-specific setup input
- Setup and review checklist Use the original recipe with the provided preparation files
- Native input scaffold: local-grid.csv Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: grid-protocol.txt Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: manifest.txt Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input scaffold: evidence-map.csv Blank editorial review input; acquire and check the stated source evidence before use; not a native export
- Native input mapping and source requirements Exact legacy mappings, required additional evidence and source-bundle gates
Optional full review prompt for prepared inputs
Prepared-input review prompt with Claude Code · prepared evidence folder
Original Law Firm Agents adaptation · untested. This prompt uses the original prepared-input schema shown in the sample test. Step prompts may use different tables. Follow NATIVE-INPUT-MAPPING where supplied; do not mix the original examples with native-step inputs without mapping and checking every field.