Frequently asked questions

Yes. Keendex processes scanned PDFs, image-based documents, and native digital PDFs. The engine reads the content regardless of how the document was originally created — no manual OCR or file conversion required before uploading.

The engine reads the entire document — not just sections labelled “Eligibility” or “Pre-Qualification.” Criteria buried in schedules, general conditions, and appendices are extracted alongside those in dedicated PQ sections. Nothing is missed because of where it sits in the document structure.

Your company profile stored in the Company Metadata Engine holds turnover figures, certifications, completed project experience, key personnel credentials, and statutory registrations. PQ Extraction compares each extracted criterion against these and flags matches, gaps, and partial matches automatically.

Yes. The Template Manager allows you to customise extraction parameters — adding sector-specific criteria, adjusting terminology for government, PSU, or private sector tenders, and prioritising the fields most relevant to your business. Templates can be saved and reused across tenders.

Yes. All extraction results are stored in your history module and accessible to team members with appropriate role permissions. Results can be exported as PDF, Word, or Excel for review in management meetings or team briefings.

Re-extraction is available at any time from the History module. Select a different AI model, re-run, and compare outputs. Both versions are stored so your team can choose the result that best serves the bid decision.

Yes. The Template Manager allows you to define a minimum weighted score — for example, any tender scoring below 50 is automatically recommended No-Go without requiring manual review. Thresholds can be set globally or varied by tender value or sector.

PQ cross-reference answers one question: do we qualify? Go/No-Go answers five: do we qualify, can we win, does it make commercial sense, are we ready to bid, and is the risk acceptable? PQ feeds into Go/No-Go as the Qualification Fit score.

Yes. Re-run at any point after an addendum, after clarifications are answered, or after your company profile is updated. The History module stores every version so you can track how the decision evolved.

Parameters that can't be fully assessed are flagged as incomplete rather than scored at zero. The overall recommendation reflects the available data and indicates which parameters need further review.

Yes. The recommendation exports as a clean PDF or Word document with parameter scores, risk flags, source page references, and the overall recommendation. Structured for a management audience, not a technical one.

Yes. The five parameters — qualification, competition, commercial viability, readiness, and risk — apply to any competitive procurement document regardless of whether it comes from a government authority, PSU, or private sector client.

Keendex processes scanned and image-based PDFs. For very poor-quality scans, extraction accuracy may vary. The engine flags items it couldn't extract with confidence so your team knows exactly what to verify manually.

Upload all volumes as a single ZIP file. The engine processes all volumes together and extracts BOQ schedules across the full set — maintaining the correct schedule hierarchy.

Yes. The hierarchy of the original document is preserved in the extracted output — chapter breaks, sub-headings, provisional sum sections, and item groupings are maintained exactly as they appear in the tender.

The Excel export is structured with item descriptions, quantities, units, and schedule names in separate columns — compatible with standard estimation templates. Direct integration depends on the estimation software's import format.

Keendex processes multi-sheet Excel workbooks directly. The engine reads all sheets, identifies BOQ data, and structures the output — handling cases where data is spread across multiple tabs.

Yes. Upload the revised tender and re-run. The History module stores all versions, and you can compare extraction outputs to identify what changed between the original document and any addendum.

No — and it's not designed to. Risk & Compliance Audit identifies and flags risk clauses systematically across the full document. What it replaces is the manual reading process that precedes legal review — your legal team starts from a structured, prioritised risk register rather than a raw 300-page document.

Liquidated damages rates and caps, performance and security bond requirements, retention money provisions, defect liability periods, payment milestone structures, extension of time clauses, unilateral variation rights, unusual indemnity provisions, termination-for-convenience terms, and statutory compliance obligations — among others.

Yes. The Template Manager allows you to set risk thresholds — for example, any LD rate above 0.5% per week as High severity, or any performance bond above 10% of contract value. These can be configured by sector, authority type, and contract value range.

All instances are extracted and cross-referenced. If the same obligation appears in both the Special Conditions and a schedule — sometimes with different terms — both are flagged and displayed together so your team can identify any inconsistency.

Yes. Export as PDF, Word, or Excel and share directly, or give team members access via the History module with appropriate role permissions.

Yes. The engine reads contractual language regardless of authority type. For international tenders, terminology may vary by jurisdiction — the Template Manager can be configured with alternate clause terminology to ensure accurate identification.

There is no system-imposed limit on the number of queries per tender. The tendering authority's own rules may specify a maximum — Keendex displays these limits when they are stated in the tender document so your team can prioritise accordingly.

Yes. Every generated query is editable before dispatch. You can reword, add context, combine queries, or remove any that aren't relevant. The AI-generated questions are a starting point — your team has full control over the final submission.

The tendering authority receives an email with a structured Excel attachment — formatted with Serial Number, Section Name, Page Number, Clause Number, and Query text in separate columns. This is the standard format accepted by most government and PSU tendering authorities.

Yes. Every query submission is stored in the History module with full details — tender reference, queries sent, date and time of dispatch, and the authority's email. When responses are received, they can be uploaded against the corresponding query for a complete pre-bid audit trail.

Yes. Each tender has its own query set within the History module. Queries for different tenders are managed independently — no cross-contamination between bid workspaces.

Yes. For private sector RFPs, the structured query format is equally useful for raising technical or commercial clarifications directly with the client. The Excel format and professional structure are appropriate for any formal procurement process.

TenderTiger aggregates tenders from central government portals, all state e-procurement systems, major PSU platforms, infrastructure authority portals, banking and financial sector procurement, and sector-specific tendering systems — spanning hundreds of procurement sources across India.

Based on how closely a tender's category, geography, authority type, and estimated value align with your configured preferences and company profile. It is a prioritisation signal — not a qualification assessment.

Tenders are stored in your View My Tenders screen until acted on or archived. The next sync fetches all tenders published since the last successful sync — no opportunities are lost from a missed cycle.

Yes. The View My Tenders screen is accessible to all team members with appropriate role permissions. Actions taken by one team member are visible to others, preventing duplicate bid preparation.

Yes. Portal Coverage Map is powered by TenderTiger's data feed, which requires a TenderTiger account. Keendex and TenderTiger are both products of eProcurement Technologies Limited and accessible from your Keendex account.

Deadline extensions and corrigenda are picked up in the next sync cycle and updated automatically against the existing tender in your pipeline. Your team receives an alert flagging the change — the tender is not duplicated or archived, and any bid preparation work already linked to it remains intact.

Keendex supports multiple AI models across different capability and cost tiers. Available models are displayed at the Model Selection step with descriptions of their strengths, processing depth, and estimated cost per extraction. The model list is updated as new models become available.

Yes. Admins can configure a default model for each extraction type — for example, a lighter model as default for PQ extractions and a more capable model as default for BOQ-heavy documents. Individual users can override the default for any specific extraction.

Token consumption is calculated based on the size of the document processed, the extraction sections selected, and the model used. Each extraction records the exact token count and corresponding cost — visible in the History module and billing dashboard.

Yes. Re-run any extraction from the History module with a different model. Both versions are stored and can be compared — so your team can select the result that best serves the bid decision.

Yes. Admins can configure model access by user role — restricting standard users to a defined set of models while allowing senior bid managers or admins to access the full roster including premium-tier models. This keeps extraction costs predictable without removing capability from the team members who need it.

Extraction costs are tracked per user and per module. Project-level or client-level cost allocation can be achieved by filtering the billing dashboard by user or by tagging extractions to specific tender references in the History module.

For most organisations, the initial company profile setup takes 60–90 minutes — entering structured data across six sections and uploading supporting documents. Once set up, the profile is available across every tender immediately. Updates take minutes, not a full re-setup.

Update the relevant section in the Metadata Engine — new financial year turnover, renewed ISO certificate, updated bank details. The update takes effect immediately across all future auto-fills. Completed annexures from previous tenders are not affected.

Access to the Metadata Engine is role-controlled. Admin users can update the company profile. Member users can view and use the profile for auto-fill but cannot edit it — preventing accidental overwriting of verified company data.

Fields that cannot be matched to stored metadata are left blank and flagged for manual completion. The system indicates which fields were auto-filled and which require manual entry — so the team knows exactly where to focus their review.

Yes. Each metadata field that relates to a certification or registration has a document attachment slot. Uploaded files are stored against the relevant credential and surfaced automatically when that field is used in an annexure auto-fill — so your team always has the supporting document alongside the data.

Yes. All data stored in the Company Metadata Engine — including financial details, certifications, and supporting documents — is protected with AES-256 encryption. Only your team holds the decryption key. No Keendex administrator can access your plain-text company data.