diff --git a/.github/workflows/devskim.yml b/.github/workflows/devskim.yml
new file mode 100644
index 0000000..2152574
--- /dev/null
+++ b/.github/workflows/devskim.yml
@@ -0,0 +1,34 @@
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: DevSkim
+
+on:
+ push:
+ branches: [ "master", "dev" ]
+ pull_request:
+ branches: [ "master", "dev" ]
+ schedule:
+ - cron: '35 3 * * 2'
+
+jobs:
+ lint:
+ name: DevSkim
+ runs-on: ubuntu-20.04
+ permissions:
+ actions: read
+ contents: read
+ security-events: write
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v3
+
+ - name: Run DevSkim scanner
+ uses: microsoft/DevSkim-Action@v1
+
+ - name: Upload DevSkim scan results to GitHub Security tab
+ uses: github/codeql-action/upload-sarif@v2
+ with:
+ sarif_file: devskim-results.sarif
diff --git a/.github/workflows/super-linter.yml b/.github/workflows/super-linter.yml
new file mode 100644
index 0000000..15719c7
--- /dev/null
+++ b/.github/workflows/super-linter.yml
@@ -0,0 +1,29 @@
+# This workflow executes several linters on changed files based on languages used in your code base whenever
+# you push a code or open a pull request.
+#
+# You can adjust the behavior by modifying this file.
+# For more information, see:
+# https://github.com/github/super-linter
+name: Lint Code Base
+
+on:
+ push:
+ branches: [ "master", "dev" ]
+ pull_request:
+ branches: [ "master", "dev" ]
+jobs:
+ run-lint:
+ runs-on: ubuntu-latest
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v3
+ with:
+ # Full git history is needed to get a proper list of changed files within `super-linter`
+ fetch-depth: 0
+
+ - name: Lint Code Base
+ uses: github/super-linter@v4
+ env:
+ VALIDATE_ALL_CODEBASE: false
+ DEFAULT_BRANCH: "master"
+ GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
diff --git a/README.md b/README.md
index a172e75..f00bf61 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,72 @@
-# atlas
-👁🗨Hallucination detector for Large Language Models.
+# ATLAS 🌐
+
+Final year project by [Jesse Amarquaye](mailto:jesseamarquayelegendary@gmail.com "Send email") and Greatman Akomea,
+computer engineering students from [Ghana Communication Technology University](https://www.gctu.edu.gh "GCTU").
+
+## Table Of Contents
+
+- [Introduction](#introduction)
+ - [Why work on hallucination in LLMs?](#why-work-on-hallucination-in-llms)
+ - [Why Atlas?](#why-atlas)
+ - [Aims or Objectives](#aims-or-objectives)
+- [Methodology](#methodology)
+
+## Introduction
+
+Atlas is a hallucination detector for Large Language Models.
+Its main focus is on **generative text** as that is the most widely used medium for interacting with LLMs.
+
+### Why work on hallucination in LLMs?
+
+Large language models (LLMs) are revolutionizing human-computer interaction, generating increasingly _fluent_ and
+_human-like text_.
+However, a significant challenge in LLMs is their tendency to produce **hallucinations**, or factually incorrect,
+nonsensical, or misleading content.
+As humans become increasingly reliant on LLMs for information and decision-making, ensuring their reliability and
+accuracy is crucial.
+This project aims to address this challenge by developing a software for **detecting** and **mitigating**
+hallucinations in LLMs so users can rely on LLM outputs with greater confidence, leading to wider adoption and
+societal benefits and also reduces the risk of misinformation to promote responsible use of LLMs.
+
+### Why Atlas?
+
+The story of Atlas in Greek mythology is closely tied to his role in supporting the heavens. According to one myth,
+during the _Titanomachy; the war between the Titans and the Olympian gods_, Atlas sided with the Titans. After their
+defeat, Zeus condemned Atlas to bear the weight of the heavens on his shoulders for eternity.
+
+The name **Atlas** symbolizes the software's commitment to bearing the responsibility of overseeing the cognitive
+aspects of language models, maintaining their stability, and preventing them from collapsing into inaccuracies or
+hallucinations. The association with Atlas also conveys _strength_, _resilience_, and _reliability_, suggesting a
+software that can handle the weight of complex language processing tasks with steadfastness and precision.
+
+### Aims or Objectives
+
+- [x] Explore techniques for mitigating hallucinations in LLMs.
+- [ ] Develop a software for automatic detection of hallucinations in LLMs.
+- [ ] Evaluate the effectiveness of the developed tool in different LLMs.
+
+## Methodology
+
+Our approach will be the design and implementation of a software to detect or flag and mitigate
+hallucinations in LLMs.
+The ultimate objective is the creation of a browser extension to actively scan the output from LLMs and
+compare them with results from trusted sources on the web and inform the user of any occurrence of hallucinations.
+An additional feature (probably in the future) will be to find the sources of the response the LLM generated.
+
+
+
+ View Flow Diagram
+
+
+
+
+
+### What we plan to do
+
+- [ ] Create a site to test how atlas will detect hallucinations in LLMs.
+- [ ] Create browser extension to finally test how atlas will operate.
+
+### What we do not plan to do
+
+- ~~Detecting and mitigating hallucination in images generated by LLMs.~~
+- ~~Detecting and mitigating hallucination in videos generated by LLMs.~~
diff --git a/docs/img/flow.png b/docs/img/flow.png
new file mode 100644
index 0000000..cba367c
Binary files /dev/null and b/docs/img/flow.png differ
diff --git a/docs/img/flow.svg b/docs/img/flow.svg
new file mode 100644
index 0000000..fab05ff
--- /dev/null
+++ b/docs/img/flow.svg
@@ -0,0 +1,2 @@
+
\ No newline at end of file