⚔️ Askalot.io
Get Started

The Research Operating System
with mathematically verified questionnaires.

One platform escorts the researcher from ideation to data quality analysis — design, campaign, execution, and analysis coordinated by a central Research Brief, with formal mathematical proof that the questionnaire's logic is sound before you field it.

Get Started Free Read Documentation
Ideate
Design
Campaign
Execute
Analyze
Bonus
Simulate

One platform. The whole research lifecycle.

Four specialized AI agents work from a single, evolving Research Brief — the central source of truth for every project. Ideation, design, campaign, execution, and data quality analysis stay in lockstep, with formal mathematical proof that the questionnaire's logic is sound.

roundtable.dev.askalot.io
Askalot unified research hub — the Round Table navigation linking Armiger, Targetor, SirWay, and Balansor around a central Research Brief

Armiger

Ideate & Design

Turn a research question and source documents into a Research Brief, then into a QML questionnaire with mathematical proof of logical soundness.

Targetor

Campaign

Target the right audience with AI-powered sampling strategies and demographic distribution.

SirWay

Execute

Execute surveys via magic links, interviewer-assisted interviews (phone & in-person), or AI simulation with persona profiles.

Balansor

Data Quality Analysis

Weight, measure, and defend your dataset — raking, representativeness metrics, straightlining and speeder flags, multi-format export.

See the full lifecycle
armiger.dev.askalot.io
Armiger - the Research Assistant agent producing a structured Research Brief (research goal, measurable metrics, KPIs, target audience) from uploaded research materials

A structured Research Brief with traceable citations back to your source documents

Ideate · Armiger

It starts with an idea — and the documents you already have.

Upload your available materials — research papers, regulations, clinical guidelines, policy documents, prior studies. The Research Assistant agent ingests and semantically indexes them, then collaborates with you to define the research goal, measurable metrics, KPIs, target audience, and questionnaire format — all captured in the Research Brief, the source of truth that travels with the project through every stage.

  • Document ingestion — PDF, Word, spreadsheets, plain text; semantically indexed for retrieval across large sets
  • Collaborative scoping — the agent proposes research goals, measurable constructs, KPIs, target audience, and the questionnaire format; you steer and approve
  • Research Brief — the approved brief becomes the contract every later stage and agent reads from
  • Project isolation — indexed documents are scoped to your project for team-level data separation
Social Research Market Research Risk & Compliance Legal Discovery Critical Systems Healthcare & Triage Clinical Due Diligence
Design · Armiger

From an approved brief to a questionnaire proven sound.

With the Research Brief approved, you or the Designer agent author the questionnaire in QML — conditional logic, skip patterns, and the right response controls. The SMT solver then mathematically proves there are no circular dependencies, no dead ends, and no contradictions, iterating generate → validate → fix until every path is sound.

  • AI generates QML from natural language or document ingestion
  • SMT solver validates reachability and logical consistency
  • Iterative refinement loop: generate → validate → fix → re-validate
  • Browser-based IDE with syntax highlighting and flow visualization
  • Support for 8+ research domains (market research, clinical, due diligence, IT security...)
Launch Armiger
armiger.dev.askalot.io
Armiger - QML questionnaire editor with React-Flow flow diagram and live item preview

SMT Validation Passed

Every item reachable · all postconditions satisfiable · 0 contradictions

targetor.dev.askalot.io
Targetor - Campaign management with sampling strategies, demographic targeting, and quality scoring
targetor.dev.askalot.io
Targetor - AI-assisted sampling strategy configuration with stratification factors and quality scoring
Campaign · Targetor

Target the right audience. Field it in waves.

With the Campaign Manager agent, define a sampling strategy, generate respondent pools with quality scoring, and plan the campaign as a single run or recurrent waves. Targetor generates the actual surveys from the campaign and assigns them to interviewers — via a guided wizard, conversational chat, or the 80+ MCP tools.

  • AI-powered campaign wizard with conversational interface
  • Sampling strategies with demographic distribution factors
  • Greedy and random-constrained pool generation with RMSE quality scoring
  • Campaign management with progress tracking and invitation dispatch
  • Interviewer workload distribution and assignment management

A guided 5-step wizard — or conversational chat for power users

1
Campaign design — name, questionnaire, mode
2
Target audience — demographics, sample size
3
Sampling strategy — stratification factors, distributions
4
Respondent pool — generate and preview quality
5
Review & launch — summary, validation, deployment

Monitor & groom — not just this campaign

Track response rates across every running study, refine a campaign mid-flight, and adjust interviewer assignments or respondent pools as the field evolves — recurrent waves keep collecting against the same strategy.

Launch Targetor
Execute · SirWay

Field surveys with logic that can't contradict itself.

Two execution paths: respondents complete surveys directly via magic links, or interviewers facilitate interviews by phone or in person. SirWay computes each next question lazily from preconditions, so respondents see only what's relevant — and the SMT proof from the design stage guarantees navigation can never contradict itself.

  • Direct mode (magic links) and Interviewer-Assisted mode (phone & in-person)
  • Lazy evaluation: questions computed dynamically from preconditions
  • Contradiction-free navigation guaranteed by SMT validation
  • Backward navigation and progress tracking for respondents
Launch SirWay
sirway.dev.askalot.io
SirWay - Survey execution with lazy evaluation, dynamic question flow, and respondent navigation
balansor.dev.askalot.io
Balansor - Medallion data pipeline with Bronze, Silver, Gold stages, quality metrics, and multi-format export
Analyze · Balansor

Don't just export results. Defend them.

Extract responses from the surveys, QA them, then re-balance with post-stratification raking against the sampling strategy. The medallion architecture refines data (Bronze raw → Silver weighted → Gold publication-ready), and per-stage metrics quantify representativeness, completion, response patterns, and internal consistency. The Analyst agent reads the Research Brief to interpret the dataset against the original objectives, not in isolation.

  • Medallion pipeline: Bronze → Silver → Gold with full lineage
  • Raking algorithm for post-stratification weighting
  • Quality metrics: representativeness (RMSE, χ², max deviation), straightlining, speeder flags, Cronbach's α, design effect
  • Export: CSV, Excel (.xlsx), SPSS (.sav), Parquet
  • Semantic clustering turns open-ended answers into quantitative theme indicators

Open-ended → quantitative

Embeddings group free-text responses by meaning, not keywords, so similar ideas cluster even when worded differently. Choose c-TF-IDF keywords for speed or LLM labels for natural names — each theme becomes a Gold indicator column ready for cross-tabulation and export.

Launch Balansor
roundtable.dev.askalot.io
RoundTable - synthetic respondent simulation with persona-driven, agentic per-question response generation
Bonus · Simulate · Roundtable

Pressure-test the whole project before a single human answers.

Beyond the five-stage lifecycle, Roundtable can simulate an entire research project with synthetic respondents — for validating questionnaire flow, exercising the analysis pipeline, or generating demo datasets. Response generation has multiple levels: lightweight statistical fills for speed, up to the heaviest mode where each respondent is a unique persona and Claude Haiku answers question by question with the persona, demographics, and accumulated Q&A history — so a respondent who said "unemployed" won't describe a workplace later.

Single

One survey, one persona

Campaign

Full 3-phase lifecycle

Mass Fill

Bulk synthetic data

  • Multiple generation levels — from fast statistical fills to agentic per-question responses
  • Three-phase flow: Preparation → Execution → Analysis
  • Exercise the Bronze → Silver → Gold pipeline with synthetic data before fielding
Young Professional Married Family Retired Senior High-Income Executive Random
Launch Roundtable
λ SMT · formal verification

Survey logic, mathematically proven.

Imperative skip logic turns into spaghetti fast — and a single contradiction can silently corrupt your data. In QML, each question simply declares when it's relevant; the compiler derives the flow and hands the whole model to the SMT solver, which proves it sound before you field it. Not only tested on a handful of paths — proven on all of them.

Every question reachable

No item is stranded behind conditions that can never all be true. If a question can't be reached, you find out before launch — not after the data comes back wrong.

Zero contradictions

Preconditions across the whole flow are checked for satisfiability, so no respondent is ever routed into a logically impossible state.

No dead ends or cycles

Cycle and dead-end analysis guarantees every path leads somewhere and the questionnaire always terminates.

QML compiler & validator — open source Read: “Stop writing survey logic as spaghetti” Peer-reviewed paper — coming soon

80+ tools. One unified API.

Every platform capability is accessible via REST API and Model Context Protocol (MCP). Drop Askalot into Claude Code, Cursor, Claude Desktop, or your own agentic framework — use whichever model you prefer. The full research lifecycle becomes tool calls for your agent.

5 Project Management
5 Questionnaires
9 Campaigns
6 Respondents
8 Pools
6 Strategies
4 Workload
8 Surveys
2 Users
8 Datasets
3 Audit
3 Documentation
MCP Tool Call 
// AI agent creates a campaign via MCP
create_campaign({
  name: "Q1 National Survey",
  project_id: "proj_abc123",
  questionnaire_id: "qst_def456"
})

// Then generates a representative sample
generate_pool_from_strategy({
  strategy_id: "str_ghi789",
  pool_name: "National Sample Q1"
})

Built for research organizations that demand rigor.

Dedicated & On-Prem Deployment

Need full isolation? We can stand up a dedicated single-tenant organization — custom domain, independent database, and complete resource isolation — in any cloud, or on your own premises.

GDPR Compliant

Full audit trails, data processing controls, and respondent consent management built into every workflow.

Role-Based Access

Admin, Designer, Manager, Interviewer — granular permissions at project, campaign, and resource level.

Full Audit Trail

Every action tracked with entity history, actor identification, and time-series event storage for compliance.

Peer-Reviewed Methodology

Agents consult ~30 survey-methodology books and papers across the full research process — Dillman, Krosnick, Groves, Tourangeau, Bethlehem — and cite the passage they used.

Askalot Plugin

Install our open Claude Code plugin — the agents, JIT skills, slash commands, and MCP tools — drives the full research lifecycle from your own harness.

View on GitHub

Genuinely free — for every researcher.

No trial clock, no credit card. Register and use the whole research lifecycle — design, campaign, execution, and analysis, with questionnaire validation. Ask for a dedicated private organization where the whole team collaborates.

Create Free Account Request Private Org Try the Live Demo

Free for university and non-profit research that isn't funded by an external source.

Or skip the signup — log in with [email protected] / demo for a read-only tour of the whole research lifecycle.